The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently better answers. o3-pro is available in the Responses API only to enable support for multi-turn model interactions before responding to API requests. Since o3-pro is designed to tackle tough problems, some requests may take several minutes to finish.
Input: Text, Image
Output: Text
Providers
openai
Credits
Context200k
Max Output100k
Input$20.00/1M
Output$80.00/1M
Cache Read—
Cache Write—
helicone
Credits
Context200k
Max Output100k
Input$20.00/1M
Output$80.00/1M
Cache Read—
Cache Write—
openrouter
Credits
Context200k
Max Output100k
Input (Max)$21.10/1M
Output (Max)$84.40/1M
Cache Read—
Cache Write—
Quick Start
Use OpenAI o3 Pro through Helicone's AI Gateway with automatic logging and monitoring.