o1

OpenAI

The o1 model series is designed to spend more time thinking before responding. 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.

Try Now

Capabilities

Tool Use

Image Input

PDF Input

Technical Specifications

Context Window

200,000 tokens

Max Output

100,000 tokens

Pricing

Token Costs (per 1M tokens)

Cache Miss Input

$15

Non-Reasoning Output

$60

Cache Read Input

$7.50

Tool Costs (per 1K calls)

Web Search

$15

Code Execution

$0.19

Legacy

Made legacy on

Reason

Superseded by o3 with better reasoning at lower cost

Recommended Replacement

GPT-5.5