TPSTokens Per Second

MiniMax M3.1 Flash

MiniMax🇨🇳 China
active
Compare with other models →
Context window1000K tokens
Input / 1M tokens$0.15
Output / 1M tokens$0.6

Version History

M3.1 Flashminor

MiniMax M3.1 Flash raises the Artificial Analysis Intelligence Index score from 29 (M3) to 42 while cutting cost per task to about $0.22. It adds a 1M-token context window with text and image input, and MiniMax claims 3x faster inference than M3.

Coverage