o4-mini
OpenAI · Released 16 Apr 2025 · o4-mini
$1.10
Input price / 1M tokens
#25 of 61, cheapest first
$4.40
Output price / 1M tokens
#27 of 61, cheapest first
200K
Context window
#62 of 71
142
Output tokens / second
#19 of 61
99.5%
AIME 2025
#1 of 7
Summary
o4-mini is a proprietary model from OpenAI, released on 16 Apr 2025.
At $1.10 input and $4.40 output per million tokens, it is #25 of 61 on input price, cheapest first.
Its 200K-token context window ranks #62 of 71.
Measured output speed is 142 tokens per second, #19 of 61.
A fast, cost-efficient o-series reasoning model for coding and visual tasks. The docs say GPT-5 mini succeeded it.
Benchmarks · 1 reported
| Benchmark | Score | Bar | Rank | Source |
|---|---|---|---|---|
| AIME 2025pass@1 with Python interpreter (100% consensus@8) | 99.5% | #1 of 7 | OpenAI launch postSelf-reported |
Self-reported means the lab ran the test itself. A rank appears only where several labs report the same version of a benchmark.
Similar models
Models with the most benchmarks in common with o4-mini, and the closest scores.
AIME 2025
#1 of 7Competition mathematics
- o4-mini99.5
- gpt-oss-20b98.7
- o398.4
- gpt-oss-120b97.9
- Gemini 3 Flash95.2
- Gemini 2.5 Pro88
Compare o4-mini side by side
Pre-filled with the two closest models. Swap any of them.
Sources
- price, tiers: developers.openai.com/api/docs/pricing, checked 2 Oct 2026
- context, max output, knowledge cutoff, snapshot: developers.openai.com/api/docs/models/o4-mini, checked 2 Oct 2026
- shutdown date Oct 23 2026, replacement: developers.openai.com/api/docs/deprecations, checked 2 Oct 2026
- release date, AIME result: openai.com/index/introducing-o3-and-o4-mini/, checked 2 Oct 2026
- output speed: artificialanalysis.ai/models/o4-mini, checked 2 Oct 2026
Building on o4-mini?
Get the architecture right before the bill arrives.
We size caching, routing and fallbacks for your workload on a free call, and tell you where a cheaper model is good enough.