Tools
Run it on the AI Native Cloud — serverless and dedicated infrastructure. https://www.together.ai/models/minimax-m2-7
MiniMax-M2 is a large-scale mixture-of-experts (MoE) language model available for inference on Together AI's platform, accessible via both serverless and dedicated infrastructure options. The model ca
MiniMax-M2 is a large-scale mixture-of-experts (MoE) language model available for inference on Together AI's platform, accessible via both serverless and dedicated infrastructure options. The model can be run through Together AI's API, offering flexible deployment for developers and enterprises seeking scalable AI capabilities. Together AI positions this as part of its "AI Native Cloud" offering, optimized for cost-effective and high-performance model serving.
Related
- MiniMax M2.7 is now on Together AI. Trained by letting it run its own RL loop, resulting in the highest open-source score on MLE Bench Lite.
- MiniMax M2.7 is live on AI Gateway
- model page: https://ollama.com/library/minimax-m2.7
- MoBiE: Efficient Inference of Mixture of Binary Experts under Post-Training Quantization
- MoE Routing Testbed: Studying Expert Specialization and Routing Behavior at Small Scale
Source: Together AI (X) | 2026-04-12