All Models

MiniMax M2.1 Lightning

minimaxReasoningTool CallingOpen Weights

High-speed MiniMax model for low-latency coding and agent workflows

Providers4
ReleasedDec 23, 2025
Input Modalitiestext
Output Modalitiestext
Tarsk Usecoding

Available Providers (4)

ProviderModel IDInput CostOutput CostContextMax OutputDocs
LLM Gatewayminimax/minimax-m2.1-lightning$0.12/MTok$0.48/MTok196.6K131.1K
DevPass (LLM Gateway)minimax-m2.1-lightning$0.12/MTok$0.48/MTok196.6K131.1K
Vercel AI Gatewayminimax/minimax-m2.1-lightning$0.30/MTok$2.40/MTok204.8K131.1K
Ofoxminimax/minimax-m2.1-lightning$0.30/MTok$2.40/MTok204.8K131.1K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output