gpt-4o-mini-realtime-preview-2024-12-17
Azure · chat model
gpt-4o-mini-realtime-preview-2024-12-17 is listed here as a chat model from Azure. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.
Input
$0.6600 / 1M tokens
Output
$2.6400 / 1M tokens
Cached input
$0.3300 / 1M tokens
Context
4.1K
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 | $0.6600 / 1M tokens |
| Output | $2.6400 / 1M tokens |
| Cached input | $0.3300 / 1M tokens |
| Audio input | $11.0000 / 1M tokens |
| Audio output | $22.0000 / 1M tokens |
| Embedding | $0.6600 / 1M tokens |
Token limits
Context window
4.1K
Max input tokens
128.0K
Max output tokens
4.1K
Max tokens
4.1K
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 |
|---|---|---|---|---|---|
| SWE-bench Verified | 33.2% | accuracy (%) | Base model: gpt-4o (GPT-4o (2024-11-20)) | 2026-05-31 | Link |
| Aider Polyglot | 30.7% | accuracy (%) | Base model: gpt-4o (GPT-4o (2024-11-20)) | 2026-05-31 | Link |
| Aider Polyglot | 18.2% | accuracy (%) | Base model: gpt-4o (GPT-4o (2024-11-20)) | 2026-05-31 | Link |
| IFEval | 81.0% | accuracy (%) | Base model: gpt-4o (GPT-4o (2024-11-20)) | 2026-05-31 | Link |
| Design Arena - 3D | 958 Elo | Elo | Base model: GPT-4o (openai/gpt-4o) | 2026-05-31 | Link |
| Design Arena - Code Categories | 918 Elo | Elo | Base model: GPT-4o (openai/gpt-4o) | 2026-05-31 | Link |
| Design Arena - Game Development | 983 Elo | Elo | Base model: GPT-4o (openai/gpt-4o) | 2026-05-31 | Link |
| Design Arena - Website | 882 Elo | Elo | Base model: GPT-4o (openai/gpt-4o) | 2026-05-31 | Link |
| MMLU | 82.0% | accuracy (%) | Base model: gpt-4o-mini (GPT-4o mini) | 2026-05-31 | Link |
| MMLU | 82% | accuracy | Base model: GPT-4o mini (gpt-4o-mini) | 2026-05-31 | Link |
Sources
| Source links | |
| Pricing data | LiteLLM model cost map |
| Synced at | 2026-05-28 |
Docs
| Official docs |
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 |
|---|---|---|---|---|---|
| gpt-4o-mini-realtime-preview-2024-12-17 Azure | In $0.6600 / 1M tokens Out $2.6400 / 1M tokens | audiotext
Output: audio, text | Function callingParallel function callingTool choiceSystem messages | 4.1K | Current model Reference row |
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| gpt-4o-realtime-preview-2024-10-01 Azure | In $5.5000 / 1M tokens Out $22.0000 / 1M tokens | audiotext
Output: audio, text | Function callingParallel function callingTool choiceSystem messages | 4.1K | Same provider Overall 82% |
| gpt-4o-mini-realtime-preview-2024-12-17 Azure | In $0.6000 / 1M tokens Out $2.4000 / 1M tokens | audiotext
Output: audio | Function callingParallel function callingTool choiceSystem messages | 4.1K | Same provider Overall 78% Missing text |
| gpt-4o-mini-realtime-preview-2024-12-17 Azure | In $0.6600 / 1M tokens Out $2.6400 / 1M tokens | audiotext image
Output: audio | Function callingParallel function callingTool choiceSystem messages | 4.1K | Same provider Overall 76% Missing text |
| gpt-4o-realtime-preview-2024-10-01 Azure | In $5.5000 / 1M tokens Out $22.0000 / 1M tokens | audiotext image
Output: audio, text | Function callingParallel function callingTool choiceSystem messages | 4.1K | Same provider Overall 74% |
| gpt-realtime-mini-2025-10-06 Azure | In $0.6000 / 1M tokens Out $2.4000 / 1M tokens | audiotext
Output: audio, text | Function callingParallel function callingTool choiceSystem messages | 4.1K | Same provider Overall 74% Missing text |
| gpt-realtime-mini OpenAI | In $0.6000 / 1M tokens Out $2.4000 / 1M tokens | audiotext
Output: audio, text | Function callingParallel function callingTool choiceSystem messages | 4.1K | Partial I/O overlap Overall 74% Missing text |
| gpt-4o-realtime-preview-2024-10-01 Azure | In $5.0000 / 1M tokens Out $20.0000 / 1M tokens | audiotext
Output: audio | Function callingParallel function callingTool choiceSystem messages | 4.1K | Same provider Overall 63% Missing text |
| gemini-2.5-flash-native-audio-preview-09-2025 Google | In $0.3000 / 1M tokens Out $2.5000 / 1M tokens | audiotext video
Output: audio, text | Audio inputAudio output | 8.2K | Text covered Overall 62% |
| llama-2-70b replicate | In $0.6500 / 1M tokens Out $2.7500 / 1M tokens | audiotext
Output: text | Tool choice | 4.1K | Text covered Overall 59% |
| llama-2-70b-chat replicate | In $0.6500 / 1M tokens Out $2.7500 / 1M tokens | audiotext
Output: text | Tool choice | 4.1K | Text covered Overall 59% |
| qwen3-omni-30b-a3b-instruct novita | In $0.2500 / 1M tokens Out $0.9700 / 1M tokens | audiotext imagevideo
Output: audio, text | Function callingParallel function callingTool choiceSystem messages | 16.4K | Text covered Overall 58% |
| gpt-4o replicate | In $2.5000 / 1M tokens Out $10.0000 / 1M tokens | audiotext image
Output: audio, text | Function callingParallel function callingTool choiceSystem messages | N/A | Text covered Overall 56% |
| l3-70b-euryale-v2.1 novita | In $1.4800 / 1M tokens Out $1.4800 / 1M tokens | audiotext
Output: text | Function callingParallel function callingTool choiceSystem messages | 8.2K | Text covered Overall 54% |
| deepseek-v3-turbo novita | In $0.4000 / 1M tokens Out $1.3000 / 1M tokens | audiotext
Output: text | Function callingParallel function callingTool choiceSystem messages | 16.0K | Text covered Overall 51% |
| llama-3-70b replicate | In $0.6500 / 1M tokens Out $2.7500 / 1M tokens | audiotext
Output: text | Tool choice | 8.2K | Text covered Overall 51% |
| llama-3-70b-instruct replicate | In $0.6500 / 1M tokens Out $2.7500 / 1M tokens | audiotext
Output: text | Tool choice | 8.2K | Text covered Overall 51% |
| mistral.voxtral-small-24b-2507 bedrock_converse | In $0.1000 / 1M tokens Out $0.3000 / 1M tokens | audiotext
Output: text | System messagesAudio input | 8.2K | Text covered Overall 50% |
| qwen.qwen3-vl-235b-a22b bedrock_converse | In $0.5300 / 1M tokens Out $2.6600 / 1M tokens | audiotext image
Output: text | Function callingSystem messages | 8.2K | Text covered Overall 49% |
| mistral.voxtral-mini-3b-2507 bedrock_converse | In $0.0400 / 1M tokens Out $0.0400 / 1M tokens | audiotext
Output: text | System messagesAudio input | 8.2K | Text covered Overall 49% |
No models match this filter.