MiniMax-M2
MiniMax's general-purpose foundation model with strong tool use and deep search capabilities
MiniMax-M2
MiniMax • October 2025
Training Data
Up to mid 2025
MiniMax-M2
October 2025
Parameters
Not disclosed
Training Method
Mixture of Experts
Context Window
Not disclosed
Knowledge Cutoff
September 2025
Key Features
Open Source • Tool Use • Deep Search • ~100 tok/s
Capabilities
Tool Use: Excellent
Search: Excellent
Coding: Very Good
What's New in This Version
Top-five globally on Artificial Analysis benchmark at 8% of Claude Sonnet pricing
MiniMax's general-purpose foundation model with strong tool use and deep search capabilities
What's New in This Version
Top-five globally on Artificial Analysis benchmark at 8% of Claude Sonnet pricing
Technical Specifications
Key Features
Capabilities
Other MiniMax Models
Explore more models from MiniMax
MiniMax-M2.5
MiniMax's flagship model matching frontier performance at 1/20th the cost with 80.2% SWE-bench Verified
MiniMax-M2.5-Lightning
Ultra-fast variant of M2.5 generating 100 tokens per second at $1/hour continuous operation
MiniMax-M2.1
Lightweight coding-focused model with strong multi-language programming and agentic capabilities
