Back to all models
minimax
minimaxMiniMax: MiniMax M1
MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing it...
minimax/minimax-m1
Context Size
1,000K
Input Price
2,460 Ks/M
Output Price
13,530 Ks/M
Architecture
Text
Supported Parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningrepetition_penaltyseedstoptemperaturetool_choicetoolstop_ktop_p
Details
TokenizerOther
Max Completion40,000 tokens
Provider Context1,000K tokens
ModeratedNo