Back to all models

o1-pro

OpenAI · o1

available
Flagship
Latest in family

Key Metrics

Input Limit

200K tokens

Output Limit

100K tokens

Input Cost

$150.00/1M

Output Cost

$600.00/1M

Sample API Code

Required Libraries

Notes

The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide consistently better answers. o1-pro is available in the Responses API only to enable support for multi-turn model interactions before responding to API requests, and other advanced API features in the future.

Capabilities

Reasoning token support
Function calling
Structured outputs
Text input
Image input
Text output
Complex reasoning
No streaming support
No fine-tuning support
No distillation support
No predicted outputs support
Responses API only access

Supported Data Types

Input Types

Text
image

Output Types

Text

Strengths & Weaknesses

Exceptional at

Reasoning

Poor at

Speed (Slowest)

Additional Information

Latest Update

Mar 19, 2025

Knowledge Cutoff

Oct 01, 2023