o4-mini
o4-mini
ProprietaryMultimodal
About
Fast and cost-efficient reasoning model with vision support for math, coding, and visual understanding. Retired from ChatGPT February 13, 2026 but still available via API. Released April 16, 2025.
o4-mini input tokens at $1/1M, output at $4/1M.
Capabilities
VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode ExecutionPrompt CachingBatch APIAudioFine-tuning
Providers(3)
Compare all →| Provider | Input (per 1M) | Output (per 1M) | Type | |
|---|---|---|---|---|
| OpenAI API | $1.10 | $4.40 | Serverless | |
| OpenRouter | $1.1 | $4.4 | Serverless | |
| Replicate API | $1 | $4 | Serverless |
Benchmark Scores(7)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| SWE-bench Verified | 68.1 | 2025-04 | OpenAI |
| LiveCodeBench | 87.3 | 2026-04 (high reasoning mode) | https://livecodebench.github.io/performances_generation.json |
| Aider Polyglot | 72.0 | 2026-04 (high) | https://aider.chat/docs/leaderboards |
| Massive Multi-discipline Multimodal Understanding | 81.6 | — | https://mmmu-benchmark.github.io/ |
| BFCL | 53.2 | — | https://gorilla.cs.berkeley.edu/leaderboard.html |
| MMLU PRO | 83.2 | — | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro |
| MultiChallenge | 44.9 | MultiChallenge | https://labs.scale.com/leaderboard/multichallenge |
