MIMiniMax/ Minimax
MiniMax M1
minimax/minimax-m1
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...
Model information
Released
2025-06-17
Context window
1M
Max output
40K
Weights
Closed
Modalities
Input
Text
Output
Text
Identity
- Version
- minimax-m1
- Knowledge cutoff
- 2024-06-30
Capabilities
ReasoningTemperatureTool call
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| OpenRouter | minimax/minimax-m1 | openai_chat | 1M | 40K | ReasoningTool callTemperature | - | input $0.55/M · output $2.2/M | Yes | ||
| Kilo Gateway | minimax/minimax-m1 | openai_chat | 1M | 40K | ReasoningTool callTemperature | - | input $0.4/M · output $2.2/M | Yes | ||
| MiniMax (minimax.io) | minimax-m1 | custom | 1M | 40K | - | - | - | Yes |