o3-mini (reasoning)

Reasoning model (Chain of Thought). Thinks internally before answering. Ideal for math problems and hard code.

ChatOpenAI200k tokens$1.1991 / $4.7963 · 1M

openai/o3-mini

Context
200k tokens
Completion cap
100,000
Tools
Yes
JSON
Yes
Released
2025-01-31
ZDR
Verified

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

Frequently asked questions

What is o3-mini (reasoning)?
Reasoning model (Chain of Thought). Thinks internally before answering. Ideal for math problems and hard code. o3-mini (reasoning) runs on the Geek Hub API (OpenAI-compatible). Model id: openai/o3-mini.
Is o3-mini (reasoning) free?
No. Input is $1.1991 per 1M tokens and output is $4.7963 per 1M tokens on Geek Hub (markup included).
What is the context length of o3-mini (reasoning)?
o3-mini (reasoning) has a 200k tokens context window. It supports up to 100,000 completion tokens.
Does o3-mini (reasoning) support tool calling and structured outputs?
o3-mini (reasoning) accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was o3-mini (reasoning) released?
o3-mini (reasoning) was released on 2025-01-31.

More models from OpenAI