GitHub radar
Try Xiaomi's model that reads photos, video, and voice
Xiaomi MiMo is an openly licensed model that handles text, images, video, and voice, and can act as an agent — writing code, browsing the web, or reading documents from a photo. You can try it right now through Xiaomi's official API or OpenRouter, no installation required.
It's an open AI model from Xiaomi that takes text, images, video, and voice as input and can act as an agent — writing code or searching online.
When it helps
Useful if you're building an agent that needs to handle several types of input at once. You can't run it on your own laptop — it's too large for that.
Pros
- Handles text, images, video, and voice in one request
- Acts as an agent: writes code, browses the web, reads documents from photos
- Available through Xiaomi's official API and OpenRouter — no server needed
- MIT license — free to use in any project
Cons
- 309 billion parameters — self-hosting needs data-center-grade server hardware
- Takes a bit of effort to set up the API key and request format
How to set it up — step by step
- 1Open your AI agent (Claude Code, Codex) in your project folder.
- 2Send the agent the text from the block below.
- 3Check that the agent found a working way to call it — via Xiaomi MiMo Open Platform API or OpenRouter.
- 4Ask the agent to show a sample request with an image and run it.
- 5If you want to self-host, ask the agent about hardware requirements — expect data-center-level needs.
Text for your agent
Copy this and send it to your agent — Claude Code, Codex, any of them:
Show me how to try Xiaomi's MiMo model: https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL — find where I can make a request through an API or demo right now, and show me a simple example with an image.
Server hardware required — nearly 310 billion parameters cannot run on a personal computer. This is a data center model.
Open on Hugging Face▌ More finds