Agents & Editors
LibreChat
Connecting LibreChat to an Adaptive Router through a custom endpoint in librechat.yaml.
LibreChat is a self-hosted chat app. It connects to Multi-Router through a custom endpoint, which its server calls with the router header.
Creating the router
LibreChat connects through an Adaptive Router, which accepts OpenAI Chat Completions requests and serves each one with the model it names, using the organization's provider key for that model's provider. LibreChat holds only the Multi-Router API key. See Adaptive Router. To set it up:
- In Model Groups, create or choose a model group with the models LibreChat should use. See Model Group.
- In Routers, choose New router, then Adaptive Router. Name it, choose the model group, and switch on the models to serve.
- Choose the organization's provider key for each provider in the group, and create the router. Its id, such as
rt_XXXXXXXX, is on the router's page. - In API Keys, create a key with the
inferencescope. It can be limited to this router. See API Key.
Every request carries the router id in the X-MR-Router header and the API key as a Bearer token, both set in LibreChat's settings below.
Settings
Add a custom endpoint to librechat.yaml. The API key is read from an environment variable, so the file holds no secret:
Set MR_API_KEY in LibreChat's environment, such as its .env file, and restart LibreChat. With titleConvo: true, LibreChat sends an extra request to title each conversation, which also goes through the router and must name a model it serves.
Models
An Adaptive Router names models by their Multi-Router catalog id, provider/model, such as anthropic/claude-sonnet-4.6, openai/gpt-5 or google/gemini-2.5-flash. The model must be switched on in the router's model group; a request for any other model is refused with a message listing the models the router serves. The settings on this page list each model id explicitly.
models.default lists the models LibreChat offers for the endpoint. Each must be switched on in the router's model group.
Checking the setup
Sign in to LibreChat, choose the Multi-Router endpoint and a model, and say hello. The reply streams back into the chat.
The request then appears in Traffic with the Adaptive Router in the Router column and the model, tokens and cost in the request detail. A reply with the requested model or router was not found means the router id is wrong, or the API key is not allowed to use that router. See Traffic and Troubleshooting.