MiMo-V2.6-Pro-UltraSpeed is the high-speed version of Xiaomi's flagship model MiMo-V2.6-Pro. Built on the same 1-trillion-parameter MiMo-V2.6-Pro checkpoint, it delivers about 10 times faster output while maintaining the same quality as the original model. It supports a 1 million token context window and native multimodal capabilities. Optimized for agent workflows, it delivers top-tier performance in coding, vision, general Q&A, and scientific research, excels at complex long-horizon tasks, and generalizes well across agent frameworks.
Inference Service Provider
The inference service provider for xiaomi/mimo-v2.6-pro-ultraspeed is Xiaomi MiMo.
Model Capabilities
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Text Image Video Audio | Output Modality | Text |
Model Experience | Unsupported | Function Calling | Supported |
Structured Outputs | Supported | Web Search | Unsupported |
Prefix Completion | Unsupported | Context Caching | Supported |
Batch Inference | Unsupported | Fine-tuning | Unsupported |
Context Limits
| Parameter | Value | Parameter | Value |
|---|---|---|---|
Max Input Length | 1048576 | Max Output Length | 131072 |
Context Window | 1048576 | Max Input Length (Thinking Mode) | 1048576 |
Max Output Length (Thinking Mode) | 131072 | Max Chain-of-Thought Length | 131072 |
Pricing
This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.
- China (Beijing)
| Billing Item | Price (CNY) | Unit |
|---|---|---|
Input | 30 | Per 1M tokens |
Output | 60 | Per 1M tokens |
Input(Implicit Cache) | 0.25 | Per 1M tokens |
Rate Limits
- China (Beijing)
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 100 |
TPM (Tokens Per Minute) | 5,000,000 |