whichllm — Browse and compare AI model specs and pricing

Nvidia

MiniMax-M2.1

minimax

Model ID minimaxai/minimax-m2.1
Provider Nvidia
Family minimax
Status -
Knowledge Cutoff -
Release Date 2025-12-23
Input Modalities text
Output Modalities text
Context Window 204800
Input Limit -
Output Limit 131072
Tool Calling Yes
Reasoning Yes
Structured Output -
Temperature Control Yes
Open Weights Yes
Input Cost / 1M tokens -
Output Cost / 1M tokens -
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens -
Cache Write Cost / 1M tokens -