o3 Mini
o3 Mini is a legacy integration reference; evaluate o3 before starting new work.
Use it for
- Teams maintaining an existing integration
- Workloads that can use a 200k context window
- Buyers comparing 4 tracked provider routes
Do not use it for
- New production launches
- Vision or document-understanding workloads
- Family
- o3
- Released
- 2025-01-31
- Context
- 200k
- Max output
- 100,000
- Architecture
- Decoder Only
- Knowledge cutoff
- 2025-04
- Specialization
- general
- License
- Proprietary
- Training
- finetuned
Cheapest of 4 routes · OpenRouter
This model is deprecated. OpenAI recommends switching to o3.
About
OpenAI o3-mini - cost-optimized reasoning model. Compact variant of reasoning model family.
o3 Mini is a proprietary model in the o3 family. The structured metadata tracks a 200k-token context window, reasoning, function calling, tool use, structured outputs, and code execution. This page tracks provider routes through OpenRouter, Azure OpenAI, OpenAI API, and 1 more, with the cheapest tracked route listed at $1.1 input and $4.4 output per 1M tokens. Headline tracked benchmarks include Aider Polyglot 60.4, Chatbot Arena 1335.0, and Google-Proof Q&A 79.7.
Top use-case fit: coding, agents, and build tasks
Coding
2 relevant benchmarks in the decision map.
RAG
Included by capability and metadata signals in the decision map.
Agents
1 relevant benchmark in the decision map.
Provider price ladder
Compare all 4Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Batch in / out | Cache | Route |
|---|---|---|---|---|---|
| OpenRouter | $1.10 | $4.40 | - | - | Serverless |
| Vercel AI Gateway | $1.10 | $4.40 | - | read $0.550 | Serverless |
| Azure OpenAI | - | - | $0.150 / $0.600 | - | ServerlessPartial |
| OpenAI API | - | - | $0.150 / $0.600 | - | ServerlessPartial |
Capabilities
Benchmark peer barsfor Coding
Benchmark scores(6)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| Aider Polyglot | 60.4 | 2026-04 (high) | https://aider.chat/docs/leaderboards |
| Chatbot Arena | 1335.0 | — | https://lmarena.ai |
| Google-Proof Q&A | 79.7 | — | https://openai.com/blog/openai-o3-mini |
| MMLU PRO | 79.1 | — | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro |
| AIME 2024 | 87.3 | — | https://openai.com/blog/openai-o3-mini |
| SWE-bench Verified | 49.3 | — | https://openai.com/blog/openai-o3-mini |
Migration checks
No linked migration route is available for this model yet.