O4 Mini
OpenAI
openai/o4-mini
Compact reasoning with tools
Context Window
200K
200,000 tokens
Max Output
100K
100,000 tokens
About this model
o4-mini is OpenAI's latest compact reasoning model with tool calling and function execution support. It combines the reasoning depth of the o3 series with the speed advantages of the mini series.
Outstanding in mathematical reasoning, logical analysis, and code debugging, at a much lower price than standard o3. Supports 200K context and vision input.
Highlights
Reasoning + tool calling
200K context
Strong math reasoning
Much cheaper than o3
Best For
Math & logical reasoningCode debuggingReasoning with toolsStructured output
2025-04-16TransformerProprietary
Capabilities
ChatVisionReasoningCodepdftoolscache
Aliases
o4-miniPricing (per 1M tokens)
| Pricing (per 1M tokens) | / 1M tokens |
|---|---|
| Input / 1M | $1.16 |
| Output / 1M | $4.62 |
| Cache Read | $0.29 |
Final prices shown
Quick Start
main.py
from openai import OpenAI client = OpenAI( base_url="https://api.chuizi.ai/v1", api_key="ck-your-key-here", ) response = client.chat.completions.create( model="openai/o4-mini", messages=[{"role": "user", "content": "Hello!"}], ) print(response.choices[0].message.content)