Model Overview
MiniMax · Active Model
- Long-Context
- API Available
- Production Ready
MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing it...
- Developer
- MiniMax
- Release Date
- June 17, 2025
- Context Window
- 1,000,000 tokens≈ 1,333 words
- API Access
- Publicly AvailableIntegrate via official API
- Input Cost
- $0.40per million tokens
- Output Cost
- $2.20per million tokens