o1-pro (batch)

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.

ChatOpenAI200k tokens$81.7545 / $327.0179 · 1M

openai/o1-pro:batch

Context
200k tokens
Completion cap
100,000
Tools
No
JSON
Yes
Released
2025-03-19

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/o1-pro:batch",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is o1-pro (batch)?
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 (batch) runs on the Geek Hub API (OpenAI-compatible). Model id: openai/o1-pro:batch.
Is o1-pro (batch) free?
No. Input is $81.7545 per 1M tokens and output is $327.0179 per 1M tokens on Geek Hub (markup included).
What is the context length of o1-pro (batch)?
o1-pro (batch) has a 200k tokens context window. It supports up to 100,000 completion tokens.
Does o1-pro (batch) support tool calling and structured outputs?
o1-pro (batch) does not advertise tool calling on this endpoint. It also supports structured outputs via a JSON schema in response_format.
When was o1-pro (batch) released?
o1-pro (batch) was released on 2025-03-19.

More models from OpenAI