MiniMax M3.1 Flash for JanitorAI: Free Proxy Setup on Composite
At a glance
| Model ID | minimax/minimax-m3.1-flash |
|---|---|
| Free ID | minimax/minimax-m3.1-flash:free |
| Made by | MiniMax |
| Context window | 1,048,576 tokens |
| Longest reply | 524,288 tokens |
| Input | Text, images, video |
| Reasoning | Always on (low to max) |
| 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
minimax/minimax-m3.1-flash:freeas the model name. - Send a short message to check the connection before you load a long chat.
MiniMax M3.1 Flash is a multimodal model from MiniMax. MiniMax describes it as a clear step up from M3, especially on complex agent tasks, coding and cybersecurity. It reads text, images and video, has a window of just over a million tokens, and can write very long replies.
It always reasons
Thinking cannot be turned off on this model; you can only choose how much. Without a setting, a reply can take a long time to start, which suits plot-heavy scenes more than quick back-and-forth chat. For ordinary roleplay, add the lowest effort to the model name: minimax/minimax-m3.1-flash:free[low]. Use [high] or [max] when a scene needs careful logic. Turn streaming on in JanitorAI so the app does not give up while the model thinks.
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 and structured output.
Your daily allowance
Each call on the free ID counts as several of the shared 80 requests, and the reasoning effort does not change that. The Models page shows the current count. If you want more replies per day for casual chat, Mistral Nemo counts as one.
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": "minimax/minimax-m3.1-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 minimax/minimax-m3.1-flash:free. The plain minimax/minimax-m3.1-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 minimax/minimax-m3.1-flash on credits or a plan, or to Synth.