whichllm — Browse and compare AI model specs and pricing

Azure Cognitive Services

o3-mini

o-mini

Model ID o3-mini
Provider Azure Cognitive Services
Family o-mini
Status -
Knowledge Cutoff 2024-05
Release Date 2024-12-20
Input Modalities text
Output Modalities text
Context Window 200000
Input Limit -
Output Limit 100000
Tool Calling Yes
Reasoning Yes
Structured Output -
Temperature Control No
Open Weights No
Input Cost / 1M tokens $1.10
Output Cost / 1M tokens $4.40
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens $0.55
Cache Write Cost / 1M tokens -