Venice AI
MiniMax M2.5
minimax
Model ID minimax-m25
Provider Venice AI
Family minimax
Status -
Knowledge Cutoff -
Release Date 2026-02-12
Input Modalities text
Output Modalities text
Context Window 198000
Input Limit -
Output Limit 32768
Tool Calling Yes
Reasoning Yes
Structured Output -
Temperature Control Yes
Open Weights No
Input Cost / 1M tokens $0.34
Output Cost / 1M tokens $1.19
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens $0.04
Cache Write Cost / 1M tokens -