MiniMax: MiniMax M1 reasoning

openrouter
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...

Capabilities

Context Window 1M tokens
Max Output 40k tokens
Inputs
Outputs

Pricing (per 1M tokens)

Input $0.40
Output $2.20
Cache Read -
Cache Write -

Supported Parameters

frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningrepetition_penaltyseedstoptemperaturetool_choicetoolstop_ktop_p

Move Chat

Select a destination folder:

Move Folder

Select a parent folder:

Folder Settings