MiMo-V2.5 for JanitorAI: Free Proxy Setup on Composite
At a glance
| Model ID | xiaomi/mimo-v2.5 |
|---|---|
| Free ID | xiaomi/mimo-v2.5:free |
| Made by | Xiaomi |
| Context window | 1,050,000 tokens |
| Longest reply | 65,536 tokens |
| Input | Text, images, video, audio |
| Reasoning | Optional |
| Tool calling | Yes |
Use it as a JanitorAI proxy
- Create an API key on the API Keys page and link Discord on your account page (not needed with credits, a plan or your own provider key).
- In JanitorAI, open Settings → API, choose
OpenAIas the API type, and paste the full URLhttps://composite.lucidity.sh/v1/chat/completionsinto the OpenAI API URL field. - Paste the key, then type
xiaomi/mimo-v2.5:freeas the model name. - Send a short message to check the connection before you load a long chat.
MiMo-V2.5 is a native omnimodal model from Xiaomi. Xiaomi says it delivers Pro-level agent performance at roughly half the inference cost, and that its image and video understanding beats MiMo-V2-Omni. It reads text, images, video and audio, has a window of just over a million tokens, and writes replies of up to 65,536 tokens.
Very few calls a day
Free models count against the shared 80 requests a day in proportion to their price, and MiMo-V2.5 is the most expensive one on the list. On November 1, 2026, each call counted as 40 requests, which is two calls a day. A call that does not fit in what is left is refused, and nothing is charged. Use it for a single hard task, such as describing a long video or an audio clip, not for a roleplay chat.
For roleplay, use V2.6-Flash
MiMo-V2.6-Flash comes from the same family, has the same window, and costs a fraction as much of your allowance per call. It also takes min P and repetition penalty, which V2.5 does not list. V2.5 accepts temperature, top P, top K, frequency and presence penalties, stop sequences, reasoning and tools.
On credits or a plan
The paid ID, xiaomi/mimo-v2.5, has no daily count. The model page shows its price per token and what a typical call costs on a plan.
Other chat apps and the API
SillyTavern, ChubAI, Agnai and RisuAI take the same key and model name with the shorter base URL https://composite.lucidity.sh/v1.
Step-by-step setup for each app is in the JanitorAI and SillyTavern guides, and the docs hub covers the others.
From code, it is a normal OpenAI-compatible request:
curl https://composite.lucidity.sh/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "xiaomi/mimo-v2.5:free", "messages": [{"role": "user", "content": "Hello"}]}'Free access (as of November 1, 2026)
On November 1, 2026, this model is on Composite's free list as xiaomi/mimo-v2.5:free. The plain xiaomi/mimo-v2.5 stays paid. Every account shares 80 requests a day across all of the free models, separate from Synth's count, and the count resets at midnight UTC. Pricier free models count as several requests per call; the Models page shows how many. Credits and plans do not raise it.
The free list changes. Check the free models on the Models page for the current set, and the features guide for the rules. A :free id that is no longer on the list returns a model-not-found error and charges nothing. When the 80 requests are used up, requests stop with an error until the reset; Composite never charges your credits to continue. You can switch to xiaomi/mimo-v2.5 on credits or a plan, or to Synth.