o4-mini
OpenAI's most advanced small reasoning model, best-performing on AIME 2024 and 2025
o4-mini
OpenAI • April 2025
Training Data
Up to December 2024
o4-mini
April 2025
Parameters
~25 billion
Training Method
Advanced Reinforcement Learning
Context Window
200,000 tokens
Knowledge Cutoff
December 2024
Key Features
Fast Reasoning • Cost Efficient • AIME Leader
Capabilities
Efficiency: Outstanding
Math: Outstanding
Reasoning: Excellent
What's New in This Version
Best-performing benchmarked model on AIME 2024 and 2025, optimized for speed and cost
OpenAI's most advanced small reasoning model, best-performing on AIME 2024 and 2025
What's New in This Version
Best-performing benchmarked model on AIME 2024 and 2025, optimized for speed and cost
Technical Specifications
Key Features
Capabilities
Other OpenAI Models
Explore more models from OpenAI
GPT-6.1 Sol
An upgrade to GPT-6 Sol that nearly matches GPT-6 Astra on agentic coding, computer use, and professional work at one-fifth of Astra's token prices
GPT-6 Sol
The GPT-6 workhorse for complex coding and agentic workflows — Astra-level reliability at a fraction of Astra's price
GPT-6 Luna
OpenAI's most efficient model for focused, high-volume tasks — summarizing documents, extracting information, and answering quick questions
