Agents & Editors
Open WebUI
Connecting Open WebUI to an Adaptive Router through an OpenAI API connection.
Open WebUI is a self-hosted chat app. It connects to Multi-Router through an OpenAI API connection, which its server calls with the router header, so the browser never holds the Multi-Router API key.
Creating the router
Open WebUI 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. Open WebUI 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 Open WebUI 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 Open WebUI's settings below.
Settings
The connection is set with environment variables when the Open WebUI container starts. OPENAI_API_CONFIGS adds the router header and the model ids to the first connection:
The header is part of the server's connection, not of the browser's requests. Load the API key from the deployment's secret store rather than writing it in a command or a file.
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.
model_ids lists the models Open WebUI offers in its model picker. Each must be switched on in the router's model group.
Checking the setup
Sign in to Open WebUI, choose the model in a new chat, 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.