Open WebUI integration

Connect Open WebUI to Modellane as an OpenAI API connection from the admin settings or with environment variables.

Open WebUI talks to OpenAI-compatible APIs through its connections settings. Add Modellane as a connection and its models appear in the model picker.

Open WebUI is a self-hosted chat interface. It connects to OpenAI-compatible APIs as an OpenAI connection with a custom base URL and calls the Chat Completions API (POST /v1/chat/completions).

Add the connection in the admin settings#

  1. Sign in as an admin and open Settings, then Admin Settings and Connections.
  2. Under Manage OpenAI API Connections, add a connection:
ParamValue
URLhttps://usemodellane.com/v1
KeyA key from API keys
  1. Save. Open WebUI loads the model ids from GET /v1/models. If the list stays empty, add model ids such as lane-1 to the connection's model list by hand.
  2. Pick a Modellane model in the model menu of a new chat.

Or use environment variables#

For a fresh install, you can set the connection when you start the container:

Shell

docker run -d -p 3000:8080 \
  -e OPENAI_API_BASE_URL=https://usemodellane.com/v1 \
  -e OPENAI_API_KEY=your-api-key \
  -v open-webui:/app/backend/data \
  --name open-webui ghcr.io/open-webui/open-webui:main

To keep another provider next to Modellane, use the plural variables OPENAI_API_BASE_URLS and OPENAI_API_KEYS with the values separated by semicolons.

Verify#

Start a new chat with the Modellane model and send "Reply with the word ready." A reply means the connection works. An authentication error points at the key, and model_not_found at the model id.

Images#