o4-mini
ReasoningClosed weightsTextReasoning
o-series family model by OpenAI.
About the o-series family
OpenAI's dedicated reasoning line (o1, o3, o4-mini, plus pro/mini variants) — models trained with reinforcement learning to 'think' in long hidden chains before answering. o1 (2024) pioneered the approach; o3/o4 refined it.
All o-series modelsHow this one is configured
This configuration runs in reasoning mode (thinks step-by-step before answering).
Also runs at: high effort
Effort controls how long the model thinks before answering — higher effort usually means better answers on hard problems, at the cost of speed and money. Same model underneath, so they share this page.