Skip to main content

Overview

Open WebUI is an open-source, self-hosted chat interface. It supports OpenAI-compatible endpoints directly in the UI, so adding the AI Gateway as a connection routes every chat through Orq.ai with the full model catalog, unified tracing, and cost tracking. This page covers model routing and tracing only.

Prerequisites

Setup

1

Start Open WebUI

Run the container, then open http://localhost:3000 and create the admin account (the first user to sign up becomes the admin):
docker run -d -p 3000:8080 -v open-webui:/app/backend/data --name open-webui ghcr.io/open-webui/open-webui:main
For other install methods, see the Open WebUI quick start.
2

Add the AI Gateway as an OpenAI connection

Go to SettingsAdmin SettingsConnections, then add a connection under OpenAI API:
  • URL: https://api.orq.ai/v3/router exactly, with no trailing path
  • Auth: Bearer
  • API Key: the Orq.ai API key
Leave Model IDs empty to include every enabled model from the AI Gateway, then Save.
Open WebUI Edit Connection panel with the URL set to the orq.ai v3 router endpoint and Auth set to Bearer with an API Key field
3

Select a model

Enabled Orq.ai models appear in the selector at the top of a new chat. To curate the list, go to Admin Settings → Models and add provider-prefixed IDs (for example openai/gpt-4o, anthropic/claude-sonnet-4-6) from Workspace Settings → Models.

Troubleshooting

The connection URL has an extra or trailing path, or the model fetch did not run. Confirm the URL is exactly https://api.orq.ai/v3/router, or add models manually under Admin Settings → Models.
A different connection is handling the request. Make sure the AI Gateway connection is selected, and disable any direct OpenAI connection to route exclusively through Orq.ai.
Confirm the API Key is a valid Orq.ai API key, not an OpenAI key.

Verification

Start a new chat, choose an Orq.ai model, and send a message. The response appears in the chat, and the request appears in Orq.ai Traces with the selected model identifier.