OpenAI: o1
OpenAI's o1 is a strong reasoning model with impressive benchmark scores across GPQA, MMLU-Pro, and coding tasks, and supports vision and tool use with a 200K context window. However, its very high pricing and the availability of more capable successors in the o3 and GPT-5 families limit its overall value for businesses today.
Assessment date: March 12, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. The o1 models are optimized for math, science, programming, and other STEM-related tasks. They consistently exhibit PhD-level accuracy on benchmarks in physics, chemistry, and biology. Learn more in the launch announcement.
Capabilities
Architecture
| Modality | Text + Image + File → Text |
| Tokenizer | GPT |
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Evaluations
Benchmark data from Artificial Analysis and Hugging Face
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $15.00 | $0.015000 |
| Output | $60.00 | $0.060000 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
