MiniMax M2
Specifications
- Input
- Output
- Context window
- 197K tokens
- Released
- Oct 2025
Performance
- Speed
- 68 t/s
- TTFT
- 2.0s
- Latency
- 1.3s
- Intelligence
- —
Pricing
- Input
- €0.25 per 1M tokens
- Output
- €1.00 per 1M tokens
About this model
MiniMax M2 is a powerful MoE model with 200B total / 10B active parameters. Optimized for reasoning and coding tasks with excellent performance in multilingual scenarios. Features 128K context window and efficient inference.
Technical specifications
- Capabilities
- Input modalities
- Output modalities
- Reasoning
- Default on
Knowledge horizon
Released Oct 2025
Today
Since release 8 mo
See also
Add Model to Comparison
Search for a model to add