Compare
o1
Comparing 1 model
| o1 | |
|---|---|
| Overview | |
| Status | Active |
| Released | 12/5/2024 |
| Summary | Reasoning-focused model that thinks before answering. |
| Pricing (per 1M tokens) | |
| Input | $15/1M |
| Output | $60/1M |
| Context and limits | |
| Context window | 200K |
| Max output | 100K |
| Modalities | |
| Supported | text, image |
| Capabilities | |
| Tool calling | Yes |
| Structured outputs | Yes |
| Open source | No |
| License | — |
| Benchmarks | |
| Aider Polyglot % pass@2 | 61.7 Third-party |
| AIME 2024 % accuracy | 83.3 Self-reported |
| GPQA Diamond % accuracy | 78 Self-reported |
| MATH % accuracy | 94.8 Self-reported |