MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding tasks. Its 1M context window supports complete documents, extended conversations, and complex task contexts in a single pass, making it ideal for integration with agent frameworks where strong reasoning, rich perception, and cost efficiency all matter.
function_calling| Model | Context | Max out | Pricing |
|---|---|---|---|
| mimo-v2-flash | 262K | 66K | $0.1$0.3 |
| mimo-v2.5 | 1.1M | 131K | $0.12$0.24 |
| mimo-v2.6-flash | 1.1M | 131K | $0.12$0.24 |
| mimo-v2.5-pro | 1.1M | 131K | $0.3$0.61 |
| mimo-v2.6-pro | 1.1M | 131K | $0.37$0.74 |
| mimo-v2-pro | 1M | 131K | $1$3 |
| mimo-v2.5-pro-ultraspeed | 1M | — | $1.3$2.61 |
| mimo-v2.6-pro-ultraspeed | 1M | 131K | $4.35$8.7 |
/v1/models/vercel/xiaomi/mimo-v2.5MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding tasks. Its 1M context window supports complete documents, extended conversations, and complex task contexts in a single pass, making it ideal for integration with agent frameworks where strong reasoning, rich perception, and cost efficiency all matter.