OpenAI model product
o3 mini
A smaller variant of O3, expected to offer enhanced multimodal capabilities, improved reasoning, and more efficient resource utilization compared to previous models while maintaining strong performance on core tasks.
Updated Aug 12, 2026. Default version: o3-mini
LLMBoard score36.3o3-mini
Coverage100%25 benchmark families
Context window200KTokens
Official input price$1.1OpenAI API
o3 mini Specifications
Technical details for the model's default version.
- Version
- o3-mini
- Released
- Jan 30, 2025
- Knowledge cutoff
- Sep 30, 2023
- Parameters
- N/A
- Context window
- 200K
- Max output
- 100K
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
o3 mini Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
o3 mini Benchmark Results
Benchmark scores for o3-mini.
| LiveBench | 84.6% | 01 | 38 | 100.0% | C | |
| MATH | 97.9% | 01 | 71 | 100.0% | C | |
| Multilingual MMLU | 80.7% | 01 | 5 | 100.0% | C | |
| COLLIE | 98.7% | 02 | 10 | 88.9% | C | |
| MGSM | 92.0% | 02 | 31 | 96.7% | C | |
| Multi-IF | 79.5% | 02 | 20 | 94.7% | C | |
| Aider-Polyglot Edit | 60.4% | 03 | 10 | 77.8% | C | |
| Internal API instruction following (hard) | 50.0% | 03 | 7 | 66.7% | C | |
| SWE-Lancer | 18.0% | 04 | 4 | 0.0% | C | |
| IFEval | 93.9% | 05 | 65 | 93.8% | C | |
| ComplexFuncBench | 17.6% | 06 | 7 | 16.7% | C | |
| SWE-Lancer (IC-Diamond subset) | 7.4% | 06 | 6 | 0.0% | C | |
| Graphwalks parents <128k | 58.3% | 07 | 11 | 40.0% | C | |
| Aider-Polyglot | 66.7% | 09 | 22 | 61.9% | C | |
| Graphwalks BFS <128k | 51.0% | 09 | 11 | 20.0% | C | |
| OpenAI-MRCR: 2 needle 128k | 18.7% | 09 | 9 | 0.0% | C | |
| AIME 2024 | 87.3% | 12 | 53 | 78.8% | C | |
| FrontierMath | 9.2% | 15 | 17 | 12.5% | C | |
| TAU-bench Airline | 32.4% | 21 | 23 | 9.1% | C | |
| TAU-bench Retail | 57.6% | 21 | 25 | 16.7% | C | |
| Multi-Challenge | 39.9% | 23 | 29 | 21.4% | C | |
| MMLU | 86.9% | 27 | 100 | 73.7% | C | |
| SimpleQA | 15.0% | 37 | 46 | 20.0% | C | |
| SWE-Bench Verified | 49.3% | 89 | 105 | 15.4% | C | |
| GPQA | 77.2% | 98 | 234 | 58.4% | C |
o3 mini Arena Results
Preference and agent-evaluation results for the default version.
| text style control | overall | 177 | 1363.5 | 18,589 | N/A | |
| text | overall | 192 | 1336.7 | 18,589 | N/A | |
| text style control | overall | 194 | 1347.9 | 57,452 | N/A | |
| text | overall | 208 | 1319.3 | 57,452 | N/A |
o3 mini Runtime Performance
Provider-specific output speed and catalog latency for o3-mini. Runtime does not affect the capability score.
| Azure | 115 tok/s | 5.2 s | 200K | 100K | |
| OpenAI | 115 tok/s | 5.2 s | 200K | 100K |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
o3 mini Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $1.1 input, $4.4 output per 1M
- Official provider
- OpenAI
- Lowest third-party
- From $0.99 input, $4 output per 1M via Poe
- Tracked offerings
- 17
| Poe | openai/o3-mini | global | $0.99 | $4 | 200K | |
| Impossibl | openai/o3-mini | global | $1.1 | $4.4 | 200K | |
| NanoGPT | openai/o3-mini | global | $1.1 | $4.4 | 200K | |
| NEAR AI Cloud | openai/o3-mini | global | $1.1 | $4.4 | 200K | |
| LLM Gateway | o3-mini | global | $1.1 | $4.4 | 200K | |
| Helicone | o3-mini | global | $1.1 | $4.4 | 200K | |
| Abacus | o3-mini | global | $1.1 | $4.4 | 200K | |
| Azure Cognitive Services | o3-mini | global | $1.1 | $4.4 | 200K | |
| Azure | o3-mini | global | $1.1 | $4.4 | 200K | |
| Kilo Gateway | openai/o3-mini | global | $1.1 | $4.4 | 200K | |
| Merge Gateway | openai/o3-mini | global | $1.1 | $4.4 | 200K | |
| Vercel AI Gateway | openai/o3-mini | global | $1.1 | $4.4 | 200K | |
| OpenRouter | openai/o3-mini | global | $1.1 | $4.4 | 200K | |
| Cloudflare AI Gateway | openai/o3-mini | global | $1.1 | $4.4 | 200K | |
| Jiekou.AI | o3-mini | global | $1.1 | $4.4 | 131.1K | |
| OpenAI | o3-mini | global | $1.1 | $4.4 | 200K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
o3 mini Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| o3-mini | 36.3 | N/A | 200K | 100K | No | Proprietary |
What is o3 mini?
Key information about o3 mini and its available data.
A smaller variant of O3, expected to offer enhanced multimodal capabilities, improved reasoning, and more efficient resource utilization compared to previous models while maintaining strong performance on core tasks.
Data as of 2026-08-11.
o3 mini vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to o3 mini
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
OP
GPT-4.5
OpenAI
OP
o1
OpenAI
OP
o1 pro
OpenAI
OP
GPT-4.1
OpenAI
OP
GPT-5-nano
OpenAI
OP
GPT-5.3
OpenAI
FAQ
Common questions about o3 mini.
When was o3 mini released?
o3 mini's default version was released on Jan 30, 2025.
How much does o3 mini cost?
o3 mini's official API price is $1.1 per million input tokens and $4.4 per million output tokens via OpenAI. The lowest tracked third-party offer starts at $0.99 input and $4 output via Poe.
Who created o3 mini?
o3 mini was created by OpenAI.
What is the context window for o3 mini?
The default version has a 200K token context window.
Is o3 mini open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer o3 mini?
17 provider offerings are linked to the default version.
What models should I compare o3 mini with?
Nearby ranked alternatives include LongCat Flash Chat, Qwen3 Next 80B A3B, o1.