o1
openai/o1-2024-12-17
OpenAI’s o1 model, released on 2024‑09‑12, accepts text, image, and file inputs and generates text output. It supports tool use and reasoning, provides a context length of 200 000 tokens, costs $15 per million input tokens and $60 per million output tokens, and its weights are not open‑source.
- tool use
- structured outputs
- reasoning
At a glance
Specifications
What the API gives you
- Context window
- 200K tokens
- Max output
- 100K tokens
- Input price
- $15 / 1M tokens
- Output price
- $60 / 1M tokens
- Cache read
- $7.50 / 1M tokens
- Modalities
- text, image, file → text
- Knowledge cutoff
- Oct 31, 2023
- Released
- Sep 12, 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
- 61.7%2026-07-17
- Aider Polyglot
- 61.7%2026-07-21
- LMArena Vision
- 1168 Elo2026-07-12
- SWE-bench Verified†
- 68.2%2025-05-16
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.