whichllm — Browse and compare AI model specs and pricing

Synthetic

MiniMax-M2

minimax

Model ID hf:MiniMaxAI/MiniMax-M2
Provider Synthetic
Family minimax
Status -
Knowledge Cutoff -
Release Date 2025-10-27
Input Modalities text
Output Modalities text
Context Window 196608
Input Limit -
Output Limit 131000
Tool Calling Yes
Reasoning Yes
Structured Output -
Temperature Control Yes
Open Weights Yes
Input Cost / 1M tokens $0.55
Output Cost / 1M tokens $2.19
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens -
Cache Write Cost / 1M tokens -