Model information
Released
2026-02-12
Context window
205K
Max output
131K
Model parameters
229B
Weights
Open
Modalities
Input
Text
Output
Text
Identity
- Version
- MiniMax-M2.5
- Aliases
- MiniMax-M2.5
Resources
Capabilities
Open weightReasoningTemperatureTool call
Official price
input $0.3/M · output $1.2/M
cache read $0.03/M · cache write $0.375/M
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| GreenPT | minimax-m2.5 | openai_chat | 205K | 131K | ReasoningTool callTemperature | - | input $0.188/M · output $1.129/M | Yes | ||
| OpenCode Go | minimax-m2.5 | openai_chat | 205K | 131K | ReasoningTool callTemperature | - | input $0.3/M · output $1.2/M cache read $0.03/M | Yes | ||
| NanoGPT | minimax/minimax-m2.5 | openai_chat | 205K | 131K | ReasoningTool callStructuredTemperature | - | input $0.3/M · output $1.2/M cache read $0.15/M | Yes | ||
| CrofAI | minimax-m2.5 | openai_chat | 205K | 131K | ReasoningTool callTemperature | - | input $0.11/M · output $0.95/M cache read $0.02/M · cache write $0.375/M | Yes | ||
| Alibaba Coding Plan (China) | MiniMax-M2.5 | openai_chat | 205K | 131K | ReasoningTool callTemperature | - | input $0/M · output $0/M cache read $0/M · cache write $0/M | Yes | ||
| LLM Gateway | minimax-m2.5 | openai_chat | 205K | 131K | ReasoningTool callTemperature | - | input $0.3/M · output $1.2/M cache read $0.03/M · cache write $0.375/M | Yes | ||
| OpenCode Zen | minimax-m2.5 | openai_chat | 205K | 131K | ReasoningTool callTemperature | - | input $0.3/M · output $1.2/M cache read $0.06/M | Yes | ||
| Alibaba Coding Plan | MiniMax-M2.5 | openai_chat | 205K | 131K | ReasoningTool callTemperature | - | input $0/M · output $0/M cache read $0/M · cache write $0/M | Yes | ||
| DInference | minimax-m2.5 | openai_chat | 205K | 131K | ReasoningTool callTemperature | - | input $0.22/M · output $0.88/M | Yes | ||
| FrogBot | minimax-m2-5 | openai_chat | 205K | 131K | AttachmentsTool callTemperature | - | input $0.3/M · output $1.2/M cache read $0.03/M | Yes | ||
| Regolo AI | minimax-m2.5 | openai_chat | 205K | 131K | ReasoningTool callTemperature | - | input $0.8/M · output $3.5/M | Yes | ||
| ZenMux | minimax/minimax-m2.5 | openai_chat | 205K | 131K | ReasoningTool callTemperature | - | input $0.3/M · output $1.2/M cache read $0.03/M · cache write $0.375/M | Yes | ||
| Alibaba Token Plan | MiniMax-M2.5 | openai_chat | 205K | 131K | ReasoningTool callTemperature | - | input $0/M · output $0/M cache read $0/M · cache write $0/M | Yes | ||
| DigitalOcean | minimax-m2.5 | openai_chat | 205K | 131K | AttachmentsReasoningTool callTemperature | - | input $0.225/M · output $0.9/M cache read $0.06/M | Yes | ||
| OrcaRouter | minimax/minimax-m2.5 | openai_chat | 205K | 131K | ReasoningTool callTemperature | - | input $0.3/M · output $1.2/M cache read $0.03/M · cache write $0.375/M | Yes | ||
| MiniMax (minimax.io) | MiniMax-M2.5 | custom | 205K | 131K | ReasoningTool callTemperature | - | input $0.3/M · output $1.2/M cache read $0.03/M · cache write $0.375/M | Yes | ||
| TensorX | minimax/minimax-m2.5 | openai_chat | 205K | 131K | ReasoningTool callTemperature | - | input $0.3/M · output $1.2/M cache read $0.075/M · cache write $0.375/M | Yes | ||
| Kilo Gateway | minimax/minimax-m2.5 | openai_chat | 205K | 131K | ReasoningTool callStructuredTemperature | - | input $0.3/M · output $1.2/M cache read $0.03/M | Yes | ||
| Merge Gateway | minimax/minimax-m2.5 | openai_chat | 205K | 131K | ReasoningTool callTemperature | - | input $0.3/M · output $1.2/M cache read $0.03/M · cache write $0.375/M | Yes | ||
| Tencent Coding Plan (China) | minimax-m2.5 | openai_chat | 205K | 131K | ReasoningTool callTemperature | - | input $0/M · output $0/M cache read $0/M · cache write $0/M | Yes | ||
| Vercel AI Gateway | minimax/minimax-m2.5 | openai_chat | 205K | 131K | ReasoningTool callTemperature | - | input $0.3/M · output $1.2/M cache read $0.03/M · cache write $0.375/M | Yes | ||
| Alibaba (China) | MiniMax-M2.5 | custom | 205K | 131K | ReasoningTool callTemperature | - | input $0.3/M · output $1.2/M | Yes | ||
| NovitaAI | minimax/minimax-m2.5 | openai_chat | 205K | 131K | ReasoningTool callStructuredTemperature | - | input $0.3/M · output $1.2/M cache read $0.03/M | Yes | ||
| OpenRouter | minimax/minimax-m2.5 | openai_chat | 205K | 131K | ReasoningTool callStructuredTemperature | Reasoning required, Hugging Face: MiniMaxAI/MiniMax-M2.5 | input $0.15/M · output $0.9/M cache read $0.05/M | Yes | ||
| MiniMax Token Plan (minimax.io) | MiniMax-M2.5 | openai_chat | 205K | 131K | ReasoningTool callTemperature | - | input $0/M · output $0/M cache read $0/M · cache write $0/M | Yes | ||
| Alibaba Token Plan (China) | MiniMax-M2.5 | openai_chat | 205K | 131K | ReasoningTool callTemperature | - | input $0/M · output $0/M cache read $0/M · cache write $0/M | Yes | ||
| Qiniu | minimax/minimax-m2.5 | openai_chat | 205K | 131K | ReasoningTool callTemperature | - | input ¥0.002/K · output ¥0.008/K | Yes | ||
| Ollama Cloud | minimax-m2.5 | openai_chat | 205K | 131K | ReasoningTool call | - | - | Yes | ||
| Cortecs | minimax-m2.5 | openai_chat | 205K | 131K | ReasoningTool callTemperature | - | input $0.32/M · output $1.18/M | Yes | ||
| HPC-AI | minimax/minimax-m2.5 | openai_chat | 205K | 131K | ReasoningTool callStructuredTemperature | - | input $0.3/M · output $1.2/M cache read $0.03/M | Yes | ||
| MiniMax (minimaxi.com) | MiniMax-M2.5 | custom | 205K | 131K | ReasoningTool callTemperature | - | input $0.3/M · output $1.2/M cache read $0.03/M · cache write $0.375/M | Yes | ||
| MiniMax Token Plan (minimaxi.com) | MiniMax-M2.5 | openai_chat | 205K | 131K | ReasoningTool callTemperature | - | input $0/M · output $0/M cache read $0/M · cache write $0/M | Yes |