LLMAPI only
o1
OpenAI
Updated May 21, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Report an error
Superseded by o3
Specifications
- Type
- LLM
- Access
- API only
- Released
- December 5, 2024
- License
- Proprietary
- Context window
- 200,000 tokens
- Knowledge cutoff
- October 31, 2023
- Output speed
- 66 tok/s
- Latency (TTFT)
- 0.54s
- Input
- Text, Image
- Output
- Text
- API pricing
- $15.00 in · $60.00 out / 1M tokens
Capabilities
Function callingStructured outputWeb search
Benchmarks
Reasoning
Coding
| HumanEval | 88.1 |
| SWE-bench Verified | 41 |
| LiveCodeBench | 67.9 |
Agents
General
| MMLU | 92 |
| SimpleQA | 47 |
| LiveBench | 67 |
| MMLU-Pro | 84.1 |
| Humanity’s Last Exam | 7.7 |
Our take
The model that mainstreamed inference-time reasoning: o1 spends hidden “thinking” tokens before answering, trading latency and cost for large gains on math, science, and code. It kicked off the reasoning-model era.