o1 (batch)

The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. The o1 models are optimized for math, science, programming, and other STEM-related tasks. They consistently exhibit PhD-level accuracy on benchmarks in physics, chemistry, and biology. Learn more in the [launch announcement](https://openai.com/o1).

ChatOpenAI200k tokens$8.1754 / $32.7018 · 1M

openai/o1:batch

Context
200k tokens
Completion cap
100,000
Tools
Yes
JSON
Yes
Released
2024-12-17

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

Frequently asked questions

What is o1 (batch)?
The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. The o1 models are optimized for math, science, programming, and other STEM-related tasks. They consistently exhibit PhD-level accuracy on benchmarks in physics, chemistry, and biology. Learn more in the [launch announcement](https://openai.com/o1). o1 (batch) runs on the Geek Hub API (OpenAI-compatible). Model id: openai/o1:batch.
Is o1 (batch) free?
No. Input is $8.1754 per 1M tokens and output is $32.7018 per 1M tokens on Geek Hub (markup included).
What is the context length of o1 (batch)?
o1 (batch) has a 200k tokens context window. It supports up to 100,000 completion tokens.
Does o1 (batch) support tool calling and structured outputs?
o1 (batch) accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was o1 (batch) released?
o1 (batch) was released on 2024-12-17.

More models from OpenAI