Minimax-M2
By
MiniMax-M2 redefines efficiency for agents. It's a compact, fast, and cost-effective MoE model (230 billion total parameters with 10 billion active parameters) built for elite performance in coding and agentic tasks, all while maintaining powerful general intelligence. With just 10 billion activated parameters, MiniMax-M2 provides the sophisticated, end-to-end tool use performance expected from today's leading models, but in a streamlined form factor that makes deployment and scaling easier than ever.
Technical Specifications
File Support: Text, Markdown and PDF files
Context window: 200k tokens
Powered by a server managed by @novitaai. Learn more
Build with Minimax-M2 using the Poe API
Start by creating an API key, for use with any bot on Poe:
See the full documentation for comprehensive guidance on getting started.
More from Novita AI
Gemma-4-26B-A4B
Gemma-4-31B-N
MiniMax-Speech-2.8
MiMo-V2-Flash
Minimax-M2.7
Qwen3.5-397B-A17B
Minimax-M2.5
GLM-5
Qwen3-Coder-Next
Kimi-K2.5