OpenAI: o3 Pro

openai/o3-pro

Created Jun 10, 2025200,000 context

$20/M input tokens$80/M output tokens$10/K web search

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

OpenAI: o3 Pro

openai/o3-pro

Created Jun 10, 2025200,000 context

$20/M input tokens$80/M output tokens$10/K web search

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

Recent activity on o3 Pro

Total usage per day on OpenRouter

Prompt

127K

Reasoning

10K

Completion

Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.