o4-mini
OpenAI · chat model
o4-mini is listed here as a chat model from OpenAI. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.
Input
$1.1000 / 1M tokens
Output
$4.4000 / 1M tokens
Cached input
$0.2750 / 1M tokens
Context
100.0K
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 | $1.1000 / 1M tokens |
| Output | $4.4000 / 1M tokens |
| Cached input | $0.2750 / 1M tokens |
| Embedding | $1.1000 / 1M tokens |
| Priority input | $2.0000 / 1M tokens |
| Priority output | $8.0000 / 1M tokens |
| Flex input | $0.5500 / 1M tokens |
| Flex output | $2.2000 / 1M tokens |
Token limits
Context window
100.0K
Max input tokens
200.0K
Max output tokens
100.0K
Max tokens
100.0K
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 |
|---|---|---|---|---|---|
| AIME 2025 | 92.7% | accuracy (%) | Base model: o4-mini (OpenAI o4-mini (high)) | 2026-05-31 | Link |
| GPQA Diamond | 81.4% | accuracy (%) | Base model: o4-mini (OpenAI o4-mini (high)) | 2026-05-31 | Link |
| SWE-bench Verified | 68.1% | accuracy (%) | Base model: o4-mini (OpenAI o4-mini (high)) | 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 |
|---|---|---|---|---|---|
| o4-mini OpenAI | In $1.1000 / 1M tokens Out $4.4000 / 1M tokens | imagepdftext
Output: text | VisionFunction callingTool choicePrompt caching | 100.0K | Current model Reference row |
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| o4-mini-2025-04-16 OpenAI | In $1.1000 / 1M tokens Out $4.4000 / 1M tokens | imagepdftext
Output: text | VisionFunction callingTool choicePrompt caching | 100.0K | Same provider Overall 100% |
| o4-mini-2025-04-16 Azure | In $1.1000 / 1M tokens Out $4.4000 / 1M tokens | imagepdftext
Output: text | VisionFunction callingTool choicePrompt caching | 100.0K | Text + image covered Overall 94% |
| o4-mini-2025-04-16 Azure | In $1.2100 / 1M tokens Out $4.8400 / 1M tokens | imagepdftext
Output: text | VisionFunction callingTool choicePrompt caching | 100.0K | Text + image covered Overall 92% |
| o3 OpenAI | In $2.0000 / 1M tokens Out $8.0000 / 1M tokens | imagepdftext
Output: text | VisionFunction callingTool choicePrompt caching | 100.0K | Same provider Overall 91% |
| o3-2025-04-16 OpenAI | In $2.0000 / 1M tokens Out $8.0000 / 1M tokens | imagepdftext
Output: text | VisionFunction callingTool choicePrompt caching | 100.0K | Same provider Overall 91% |
| gpt-5.4-mini azure_ai | In $0.7500 / 1M tokens Out $4.5000 / 1M tokens | imagepdftext
Output: text | VisionFunction callingTool choicePrompt caching | 128.0K | Text + image covered Overall 89% |
| gpt-5.4-mini OpenAI | In $0.7500 / 1M tokens Out $4.5000 / 1M tokens | imagepdftext
Output: text | VisionFunction callingTool choicePrompt caching | 128.0K | Same provider Overall 89% |
| gpt-5.4-mini-2026-03-17 OpenAI | In $0.7500 / 1M tokens Out $4.5000 / 1M tokens | imagepdftext
Output: text | VisionFunction callingTool choicePrompt caching | 128.0K | Same provider Overall 89% |
| gpt-5 OpenAI | In $1.2500 / 1M tokens Out $10.0000 / 1M tokens | imagepdftext
Output: text | VisionFunction callingTool choicePrompt caching | 128.0K | Same provider Overall 84% |
| claude-3-7-sonnet-20250219 Anthropic | In $3.0000 / 1M tokens Out $15.0000 / 1M tokens | imagepdftext
Output: text | VisionFunction callingTool choicePrompt caching | 64.0K | Text + image covered Overall 78% |
| claude-4-sonnet-20250514 Anthropic | In $3.0000 / 1M tokens Out $15.0000 / 1M tokens | imagepdftext
Output: text | VisionFunction callingTool choicePrompt caching | 64.0K | Text + image covered Overall 78% |
| claude-sonnet-4-5-20250929 Anthropic | In $3.0000 / 1M tokens Out $15.0000 / 1M tokens | imagepdftext
Output: text | VisionFunction callingTool choicePrompt caching | 64.0K | Text + image covered Overall 78% |
| o3-mini Azure | In $1.1000 / 1M tokens Out $4.4000 / 1M tokens | imagepdftext
Output: text | Tool choicePrompt cachingReasoningResponse schema | 100.0K | Partial I/O overlap Overall 75% Missing image |
| o3-mini-2025-01-31 Azure | In $1.1000 / 1M tokens Out $4.4000 / 1M tokens | imagepdftext
Output: text | Tool choicePrompt cachingReasoning | 100.0K | Partial I/O overlap Overall 72% Missing image |
| o4-mini Azure | In $1.1000 / 1M tokens Out $4.4000 / 1M tokens | imagepdftext
Output: text | VisionFunction callingTool choicePrompt caching | 100.0K | Partial I/O overlap Overall 70% Missing text, image |
| o1-mini-2024-09-12 Azure | In $1.1000 / 1M tokens Out $4.4000 / 1M tokens | imagepdftext
Output: text | Function callingPrompt cachingReasoning | 65.5K | Partial I/O overlap Overall 66% Missing image |
| openai-o3-mini gradient_ai | In $1.1000 / 1M tokens Out $4.4000 / 1M tokens | imagepdftext
Output: unknown | Low overlap | 100.0K | Partial I/O overlap Overall 35% Missing text, image |
No models match this filter.