o3 Mini (batch)

OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to "high", "medium", or "low" to control the thinking time of the model. The default is "medium". The model features three adjustable reasoning effort levels and supports key developer capabilities including function calling, structured outputs, and streaming, though it does not include vision processing capabilities. The model demonstrates significant improvements over its predecessor, with expert testers preferring its responses 56% of the time and noting a 39% reduction in major errors on complex questions. With medium reasoning effort settings, o3-mini matches the performance of the larger o1 model on challenging reasoning evaluations like AIME and GPQA, while maintaining lower latency and cost.

ChatOpenAI200k tokens$0.5995 / $2.3981 · 1M

openai/o3-mini:batch

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

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

Frequently asked questions

What is o3 Mini (batch)?
OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to "high", "medium", or "low" to control the thinking time of the model. The default is "medium". The model features three adjustable reasoning effort levels and supports key developer capabilities including function calling, structured outputs, and streaming, though it does not include vision processing capabilities. The model demonstrates significant improvements over its predecessor, with expert testers preferring its responses 56% of the time and noting a 39% reduction in major errors on complex questions. With medium reasoning effort settings, o3-mini matches the performance of the larger o1 model on challenging reasoning evaluations like AIME and GPQA, while maintaining lower latency and cost. o3 Mini (batch) runs on the Geek Hub API (OpenAI-compatible). Model id: openai/o3-mini:batch.
Is o3 Mini (batch) free?
No. Input is $0.5995 per 1M tokens and output is $2.3981 per 1M tokens on Geek Hub (markup included).
What is the context length of o3 Mini (batch)?
o3 Mini (batch) has a 200k tokens context window. It supports up to 100,000 completion tokens.
Does o3 Mini (batch) support tool calling and structured outputs?
o3 Mini (batch) accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was o3 Mini (batch) released?
o3 Mini (batch) was released on 2025-01-31.

More models from OpenAI