All Models

o3-pro

o-pro Reasoning Tool Calling Attachments Structured Output

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. Note that BYOK is required for this model. Set up here: https://openrouter.ai/settings/integrations

Providers 5
Released Apr 16, 2025
Input Modalities text, image, pdf
Output Modalities text
Tarsk Use coding

Benchmarks

40.7
Intelligence Index

Available Providers (5)

Provider Model ID Input Cost Output Cost Context Max Output Docs
Poe openai/o3-pro $18.00/MTok $72.00/MTok 200K 100K
Cloudflare AI Gateway openai/o3-pro $20.00/MTok $80.00/MTok 200K 100K
Abacus o3-pro $20.00/MTok $40.00/MTok 200K 100K
Vercel AI Gateway openai/o3-pro $20.00/MTok $80.00/MTok 200K 100K
OpenAI o3-pro $20.00/MTok $80.00/MTok 200K 100K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output