OpenAI: o1 API
OpenAI o1 is the first flagship model in the reasoning series. Trained with reinforcement learning, it generates a long internal chain of thought before responding, designed specifically for complex logic, science, math, and coding tasks.
- Context window: 200,000 tokens
- Max output: 100,000 tokens
- Input: text, image
- Output: text
- Reasoning: Supported
- Tool calling: Supported
- File input: Supported
- Released: 2024-12-05
- Knowledge cutoff: 2023-09-30
Frequently Asked Questions
What is the context window of o1?
o1 supports a context window of up to 200,000 tokens.
Does o1 support function calling?
Yes. o1 supports tool / function calling.
Does o1 support reasoning?
Yes. o1 is a reasoning-capable model.
What is the knowledge cutoff of o1?
The knowledge cutoff of o1 is 2023-09-30.