o3
openai/o3-2025-04-16
OpenAI's o3, released on 2024‑06‑01, accepts image, text, and file inputs and generates text output. It supports tool usage, reasoning capabilities, and a context window of 200 000 tokens. Pricing is $0.02 per M input tokens and $0.08 per M output tokens, and the model is not open‑weights.
- tool use
- structured outputs
- reasoning
At a glance
Specifications
What the API gives you
- Context window
- 200K tokens
- Max output
- 100K tokens
- Input price
- $2 / 1M tokens
- Output price
- $8 / 1M tokens
- Cache read
- $0.50 / 1M tokens
- Modalities
- image, text, file → text
- Knowledge cutoff
- Jun 30, 2024
- Released
- Jun 1, 2024
Recommendation coverage
Where this model appears
Not currently included in a published recommendation. This means the available task-specific evidence did not support a ranking yet—not that the model was reviewed and rejected.
Measured evidence
Public benchmark record
- Aider Polyglot
- 81.3%2026-07-17
- Aider Polyglot
- 81.3%2026-07-21
- LMArena Vision
- 1215 Elo2026-07-12
- SWE-bench Verified†
- 70.4%2025-05-15
LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. † Self-reported scaffold plus model result. Treat it as a claim, not an independent measurement.
Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.