o3
Current
- Context window
- 200.000 tokens
- Max output
- 65.536 tokens
- Price input / 1M tokens
- $2.00
- Price output / 1M tokens
- $8.00
- Price cache-read / 1M
- $0.50
Capabilities
- Reasoning
- Code
- Tool use
Benchmark scores
- MMMU
- 82.9
- AIME 2024
- 96.7
- AIME 2025
- 88.9
- Codeforces
- 2,727.0
- GPQA Diamond
- 87.7
- SWE-bench Verified
- 71.7
Notes
Reasoning model from the o-series, successor to o1. Source: openai.com/api/pricing.