MiMo-V2.5
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.
xiaomi/mimo-v2.5
- Context
- 1M tokens
- Completion cap
- 131,072
- Tools
- Yes
- JSON
- Yes
- Released
- 2026-04-22
Call it from Geek Hub
Same OpenAI SDK. Change the base URL and the model id.
curl https://api.geekhub.mx/v1/chat/completions \
-H "Authorization: Bearer $GEEKHUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "xiaomi/mimo-v2.5",
"messages": [{"role": "user", "content": "Hola"}]
}'Frequently asked questions
- What is MiMo-V2.5?
- 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. MiMo-V2.5 runs on the Geek Hub API (OpenAI-compatible). Model id: xiaomi/mimo-v2.5.
- Is MiMo-V2.5 free?
- No. $0.1526 per minute on Geek Hub.
- What is the context length of MiMo-V2.5?
- MiMo-V2.5 has a 1M tokens context window. It supports up to 131,072 completion tokens.
- When was MiMo-V2.5 released?
- MiMo-V2.5 was released on 2026-04-22.