MiniMax M1
All models
MinimaxMinimax

MiniMax M1

1M context$0.400/M input$2.20/M output

MiniMax M1 is an AI model from Minimax built for agent workflows, with support for text input and text output. 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...

What is MiniMax M1?

MiniMax M1 is an AI model from Minimax that Agent Mag tracks for pricing, context window, modalities, benchmarks, and API compatibility. Builders can use this page to compare MiniMax M1 against other models for agent workflows and production deployments.

Model ID

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...

Modalities
Input
text
Output
text
Supported Parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningrepetition_penaltyseedstoptemperaturetool_choicetoolstop_ktop_p

Related content