MiniMax-M2.5 is MiniMax's flagship open-source large model, trained on large-scale reinforcement learning across real-world scenarios. It supports programming, tool calls, search, and office productivity tasks.
Inference Service Provider
The inference service provider for MiniMax-M2.5 is QwenCloud.
Model Capabilities
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Text | Output Modality | Text |
Model Experience | Supported | Function Calling | Supported |
Structured Outputs | Unsupported | Web Search | Unsupported |
Prefix Completion | Unsupported | Context Caching | Supported |
Batch Inference | Unsupported | Fine-tuning | Unsupported |
Context Limits
| Parameter | Value | Parameter | Value |
|---|---|---|---|
Max Input Length | 196608 | Max Output Length | 32768 |
Context Window | 204800 |
Pricing
This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit QwenCloud console for promotional offers.
- China North 2 (Beijing)
| Billing Item | Price (USD) | Unit |
|---|---|---|
Input | 0.304 | Per 1M tokens |
Output | 1.213 | Per 1M tokens |
Input(Implicit Cache) | 0.061 | Per 1M tokens |
Rate Limits
- China North 2 (Beijing)
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 500 |
TPM (Tokens Per Minute) | 1,000,000 |