MiniMax-M2.1 redefines efficiency for intelligent agents. It is a compact, fast and cost-effective MoE model with 230 billion total parameters and 10 billion activation parameters, built for top performance in coding and agent tasks while maintaining strong general intelligence. With only 10 billion activation parameters, MiniMax-M2 delivers the sophisticated end-to-end tooling performance expected from today's leading models, but in a more refined form factor...
Provider: MiniMaxAI
Context window: 192K
Pricing: $0.20 input / $0.67 output per 1M tokens
Capabilities: serverless, json_mode, function_calling, structured_output
