deepseek-v3
DeepSeek · chat model
deepseek-v3 is listed here as a chat model from DeepSeek. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.
Input
$0.2700 / 1M tokens
Output
$1.1000 / 1M tokens
Cached input
$0.0700 / 1M tokens
Context
8.2K
Quick read
Best for
Use this page when you need a fast view of cost, context size, and supported features before testing the model in your own workload.
Things to verify
Always check the provider page for discounts, cache pricing, region rules, and any model limits that may not appear in public metadata.
Pricing
| Item | Price |
|---|---|
| Input | $0.2700 / 1M tokens |
| Output | $1.1000 / 1M tokens |
| Cached input | $0.0700 / 1M tokens |
| Cache write | N/A 0 in raw data; semantics unverified |
| Embedding | $0.2700 / 1M tokens |
Token limits
Context window
8.2K
Max input tokens
65.5K
Max output tokens
8.2K
Max tokens
8.2K
Capabilities
| Capability | Supported |
|---|---|
| Vision | — |
| Function calling | ✅ |
| Parallel function calling | — |
| Tool choice | ✅ |
| Prompt caching | ✅ |
| Reasoning | — |
| Response schema | — |
| System messages | — |
| Audio input | — |
| Audio output | — |
| Web search | — |
| PDF input | — |
| Video input | — |
Benchmarks
Most benchmark rows are attached to the base model family rather than this provider route. Open benchmark explorer
| Benchmark | Score | Metric | Scope | Checked | Source |
|---|---|---|---|---|---|
| MMLU | 88.5 | EM | Base model: DeepSeek-V3 (DeepSeek-V3) | 2026-05-31 | Link |
| GPQA Diamond | 59.1 | Pass@1 | Base model: DeepSeek-V3 (DeepSeek-V3) | 2026-05-31 | Link |
| LiveCodeBench | 37.6 | Pass@1 | Base model: DeepSeek-V3 (DeepSeek-V3) | 2026-05-31 | Link |
| AIME 2024 | 39.2 | Pass@1 | Base model: DeepSeek-V3 (DeepSeek-V3) | 2026-05-31 | Link |
| MATH-500 | 90.2 | EM | Base model: DeepSeek-V3 (DeepSeek-V3) | 2026-05-31 | Link |
Sources
| Source links | |
| Pricing data | LiteLLM model cost map |
| Synced at | 2026-05-28 |
Similar models
This list is ranked by overall similarity. Use filters to emphasize the lens that matters most for the replacement you are making.
Comparing from
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| deepseek-v3 DeepSeek | In $0.2700 / 1M tokens Out $1.1000 / 1M tokens |
Output: unknown | Function callingTool choicePrompt caching | 8.2K | Current model Reference row |
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| eu.anthropic.claude-3-5-haiku-20241022-v1:0 Bedrock | In $0.2500 / 1M tokens Out $1.2500 / 1M tokens | pdftext
Output: text | Function callingTool choicePrompt caching | 8.2K | Partial I/O overlap Overall 48% |
| minimax.minimax-m2.1 Bedrock | In $0.3000 / 1M tokens Out $1.2000 / 1M tokens | text
Output: text | Function callingTool choice | 8.2K | Partial I/O overlap Overall 46% |
| minimax.minimax-m2.5 Bedrock | In $0.3000 / 1M tokens Out $1.2000 / 1M tokens | text
Output: text | Function callingTool choice | 8.2K | Partial I/O overlap Overall 46% |
| minimax.minimax-m2.1 Bedrock | In $0.3000 / 1M tokens Out $1.2000 / 1M tokens | text
Output: text | Function callingTool choice | 8.2K | Partial I/O overlap Overall 46% |
| minimax.minimax-m2.1 Bedrock | In $0.3000 / 1M tokens Out $1.2000 / 1M tokens | text
Output: text | Function callingTool choice | 8.2K | Partial I/O overlap Overall 46% |
| minimax.minimax-m2.5 Bedrock | In $0.3000 / 1M tokens Out $1.2000 / 1M tokens | text
Output: text | Function callingTool choice | 8.2K | Partial I/O overlap Overall 46% |
| deepseek-r1 DeepSeek | In $0.5500 / 1M tokens Out $2.1900 / 1M tokens |
Output: unknown | Function callingTool choicePrompt caching | 8.2K | Same provider Overall 44% |
| DeepSeek Chat DeepSeek | In $0.2800 / 1M tokens Out $0.4200 / 1M tokens |
Output: unknown | Function callingTool choicePrompt caching | 8.2K | Same provider Overall 40% |
| deepseek-chat DeepSeek | In $0.2800 / 1M tokens Out $0.4200 / 1M tokens |
Output: unknown | Function callingTool choicePrompt caching | 8.2K | Same provider Overall 40% |
| deepseek-coder DeepSeek | In $0.1400 / 1M tokens Out $0.2800 / 1M tokens |
Output: unknown | Function callingTool choicePrompt caching | 4.1K | Same provider Overall 40% |
| minimax-m2.5 OpenRouter | In $0.3000 / 1M tokens Out $1.1000 / 1M tokens | text
Output: text | Function callingTool choicePrompt caching | 65.5K | Partial I/O overlap Overall 40% |
| minimax-m2 OpenRouter | In $0.2550 / 1M tokens Out $1.0200 / 1M tokens | text
Output: text | Function callingTool choicePrompt caching | 204.8K | Partial I/O overlap Overall 38% |
| deepseek-v3.2-exp OpenRouter | In $0.2000 / 1M tokens Out $0.4000 / 1M tokens | text
Output: text | Function callingTool choicePrompt caching | 163.8K | Partial I/O overlap Overall 36% |
| glm-4.5-air vercel_ai_gateway | In $0.2000 / 1M tokens Out $1.1000 / 1M tokens | text
Output: text | Function callingTool choice | 96.0K | Partial I/O overlap Overall 36% |
| ernie-4.5-300b-a47b-paddle novita | In $0.2800 / 1M tokens Out $1.1000 / 1M tokens | text
Output: text | Tool choice | 12.0K | Partial I/O overlap Overall 35% |
| grok-code-fast xai | In $0.2000 / 1M tokens Out $1.5000 / 1M tokens | text
Output: text | Function callingTool choicePrompt caching | 256.0K | Partial I/O overlap Overall 34% |
| grok-code-fast-1 xai | In $0.2000 / 1M tokens Out $1.5000 / 1M tokens | text
Output: text | Function callingTool choicePrompt caching | 256.0K | Partial I/O overlap Overall 34% |
| deepseek-v3.2 DeepSeek | In $0.2800 / 1M tokens Out $0.4000 / 1M tokens |
Output: unknown | Function callingTool choicePrompt caching | 163.8K | Same provider Overall 32% |
| deepseek-v3.2 azure_ai | In $0.5800 / 1M tokens Out $1.6800 / 1M tokens | text
Output: text | Function callingTool choicePrompt caching | 163.8K | Partial I/O overlap Overall 31% |
| deepseek-v3.2-speciale azure_ai | In $0.5800 / 1M tokens Out $1.6800 / 1M tokens | text
Output: text | Function callingTool choicePrompt caching | 163.8K | Partial I/O overlap Overall 31% |
| deepseek-v3-0324 novita | In $0.2700 / 1M tokens Out $1.1200 / 1M tokens | text
Output: text | Function callingTool choice | 163.8K | Partial I/O overlap Overall 29% |
| GLM-4.5-Air-FP8 Together AI | In $0.2000 / 1M tokens Out $1.1000 / 1M tokens | text
Output: text | Function callingTool choice | N/A | Partial I/O overlap Overall 28% |
| qwen3-235b-a22b-instruct-2507 replicate | In $0.2640 / 1M tokens Out $1.0600 / 1M tokens | text
Output: text | Function calling | N/A | Partial I/O overlap Overall 26% |
| deepseek-reasoner DeepSeek | In $0.2800 / 1M tokens Out $0.4200 / 1M tokens |
Output: unknown | Prompt caching | 65.5K | Same provider Overall 19% |
No models match this filter.