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.

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.