o3 Pro

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:

ChatOpenAI200k tokens$21.8012 / $87.2048 · 1M

openai/o3-pro

Context
200k tokens
Completion cap
100,000
Tools
Yes
JSON
Yes
Released
2025-06-10

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/o3-pro",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is o3 Pro?
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: o3 Pro runs on the Geek Hub API (OpenAI-compatible). Model id: openai/o3-pro.
Is o3 Pro free?
No. Input is $21.8012 per 1M tokens and output is $87.2048 per 1M tokens on Geek Hub (markup included).
What is the context length of o3 Pro?
o3 Pro has a 200k tokens context window. It supports up to 100,000 completion tokens.
Does o3 Pro support tool calling and structured outputs?
o3 Pro accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was o3 Pro released?
o3 Pro was released on 2025-06-10.

More models from OpenAI