All Models

MiniMax M2

ReasoningTool CallingOpen WeightsStructured Output

MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...

Providers20
ReleasedOct 26, 2025
Input Modalitiestext
Output Modalitiestext
Tarsk Usecoding

Benchmarks

18.6
Intelligence Index
78.3
Math Index

Available Providers (20)

ProviderModel IDInput CostOutput CostContextMax OutputDocs
MiniMax Token Plan (minimax.cn)MiniMax-M2$0/MTok$0/MTok204.8K131.1K
MiniMax Token Plan (minimax.io)MiniMax-M2$0/MTok$0/MTok204.8K131.1K
NanoGPTminimax/minimax-m2$0.17/MTok$1.53/MTok200K131.1K
LLM Gatewayminimax/minimax-m2$0.20/MTok$1/MTok196.6K131.1K
DevPass (LLM Gateway)minimax-m2$0.20/MTok$1/MTok196.6K131.1K
OpenRouterminimax/minimax-m2$0.26/MTok$1.02/MTok204.8K131.1K
NovitaAIminimax/minimax-m2$0.30/MTok$1.20/MTok204.8K131.1K
Hugging FaceMiniMaxAI/MiniMax-M2$0.30/MTok$1.20/MTok204.8K131.1K
MiniMax (minimax.io)MiniMax-M2$0.30/MTok$1.20/MTok204.8K131.1K
Vercel AI Gatewayminimax/minimax-m2$0.30/MTok$1.20/MTok205K205K
Kilo Gatewayminimax/minimax-m2$0.30/MTok$1.20/MTok204.8K131.1K
Amazon Bedrockminimax.minimax-m2$0.30/MTok$1.20/MTok204.6K128K
Merge Gatewayminimax/minimax-m2$0.30/MTok$1.20/MTok204.8K8.2K
Ofoxminimax/minimax-m2$0.30/MTok$1.20/MTok204.8K131.1K
ZenMuxminimax/minimax-m2$0.30/MTok$1.20/MTok204K64K
MiniMax (minimax.cn)MiniMax-M2$0.30/MTok$1.20/MTok204.8K131.1K
Eden AIminimax/MiniMax-M2$0.30/MTok$1.20/MTok204.8K131.1K
302.AIMiniMax-M2$0.33/MTok$1.32/MTok1M128K
Cortecsminimax-m2$0.35/MTok$1.41/MTok400K196K
Qiniuminimax/minimax-m2—/MTok—/MTok200K128K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output