MiMo-V2.6-Flash for JanitorAI: Free Proxy Setup on Composite
At a glance
| Model ID | xiaomi/mimo-v2.6-flash |
|---|---|
| Free ID | xiaomi/mimo-v2.6-flash:free |
| Made by | Xiaomi |
| Context window | 1,050,000 tokens |
| Longest reply | 131,072 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-v2.6-flash:freeas the model name. - Send a short message to check the connection before you load a long chat.
MiMo-V2.6-Flash is an open-source foundation model from Xiaomi. It is a mixture-of-experts model with 309B total parameters and 15B active for each token, and uses a hybrid attention design to keep a window of just over a million tokens practical. It reads text, images, video and audio, and replies in text.
A good fit for chat
Reasoning is optional, so by default the model answers straight away. That makes it one of the quicker large models on the free list for back-and-forth roleplay. Turn reasoning on in your app or the request body when a scene needs planning; no effort levels are listed for it, so leave the bracket suffixes off the model ID.
Settings it accepts
It takes the full set of chat samplers: temperature, top P, top K, min P, repetition penalty, frequency and presence penalties, stop sequences and logit bias. A SillyTavern or JanitorAI preset applies as written. It also supports tool calling with parallel calls and structured output.
Compared with MiMo-V2.5
MiMo-V2.5 is also on the free list, but it is far pricier, so each of its calls takes a much bigger share of the 80 a day. For roleplay, start with V2.6-Flash; it also accepts more of a preset's settings.
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-v2.6-flash: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-v2.6-flash:free. The plain xiaomi/mimo-v2.6-flash 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-v2.6-flash on credits or a plan, or to Synth.