OpenAI o4-mini
OpenAIUpdated mini reasoning model. Similar pricing to o3-mini with updated capabilities.
OpenAI o4-mini Pricing
| Token Type | Price per Million |
|---|---|
| Input tokens | $1.10 |
| Output tokens | $4.40 |
Estimated Cost by Project Size
Realistic cost estimates for common coding scenarios. Assumes 30% cache hit rate where caching is available.
| Scenario | Token Usage | Estimated Cost |
|---|---|---|
| Small Script (1K lines) | 50K input / 30K output | $0.17 |
| Medium Feature (10K lines) | 500K input / 200K output | $1.27 |
| Large Project (50K lines) | 2,500K input / 1,000K output | $6.33 |
| Code Review (5K lines) | 250K input / 25K output | $0.30 |
Benchmark Performance — OpenAI o4-mini
Third-party benchmark scores normalized to 0-100 scale. Higher is better. Aggregated scores from published third-party benchmarks. SWE-bench measures real GitHub issue resolution. LiveCodeBench measures competitive programming ability. HumanEval measures basic code generation. BigCodeBench measures practical, multi-step coding tasks. All scores normalized to 0-100 scale.
Sources: SWE-bench Verified, LiveCodeBench, HumanEval, BigCodeBench
Get Access to OpenAI o4-mini
Ready to start using OpenAI o4-mini? Get API access directly from OpenAI.
How Does OpenAI o4-mini Compare?
| Model | Input ($/M) | Medium Feature Cost | |
|---|---|---|---|
| OpenAI o4-mini | $1.10 | $1.27 | selected |
| OpenAI o1-mini | $1.10 | $1.27 | Compare |
| OpenAI o3-mini | $1.10 | $1.27 | Compare |
| Claude Sonnet 4 Lite | $1.00 | $1.55 | Compare |
| Gemini 2.5 Pro | $1.25 | $2.44 | Compare |
| Gemini 1.5 Pro | $1.25 | $1.44 | Compare |
Related Models
Claude 3.5 Haiku
AnthropicFast, cost-effective model for high-volume tasks. Great for code review and simple queries.
Claude 3 Haiku
AnthropicCheapest Claude model. Fast responses for simple tasks and basic coding.
GPT-4o
OpenAIOpenAI's flagship multimodal model. Strong coding and reasoning at competitive pricing.
GPT-4o mini
OpenAIAffordable small model. Fast and cost-effective for high-volume coding tasks.