Integration guide

Run Open WebUI on OpenLux models

Open WebUI talks to any OpenAI-compatible endpoint. Set the connection URL to OpenLux and your self-hosted chat interface can switch between GPT-6 Astra, Claude Opus 5, Gemini 3.8 Flash and DeepSeek V4 on one key.

Create an API key Read the docs

Abstract orange glass sculpture illustrating the Open WebUI integration with OpenLux — Open WebUI + OpenLux — one key, one endpoint, one bill.

Set it up in four steps

Create an OpenLux key

Point Open WebUI at OpenLux

In Admin Panel → Settings → Connections add an OpenAI connection with the URL https://openlux.lol/v1 and your key. The model list is fetched automatically.

Pick the models you want in the picker

OpenLux serves the full catalogue through one endpoint. Add the models you care about — or leave the list open and switch per conversation.

Chat, with cost visible in the console

Every message is metered per token on the OpenLux side, so usage and spend stay auditable while Open WebUI stays exactly as it is.

Configuration

Copy these blocks, replace the placeholder key and you are done.

Docker (environment variables)

docker run -d --name open-webui -p 3000:8080 \
  -e OPENAI_API_BASE_URL="https://openlux.lol/v1" \
  -e OPENAI_API_KEY="sk-openlux-..." \
  -v open-webui:/app/backend/data \
  ghcr.io/open-webui/open-webui:main

Admin Panel → Settings → Connections

OpenAI API
  URL:  https://openlux.lol/v1
  Key:  sk-openlux-...
  Models: fetched automatically (or add gpt-6-astra, claude-opus-5, deepseek-v4)

Models that fit Open WebUI

GPT-6 Astra

OpenAI · $0.3677 / 1M tokens

Claude Opus 5

Anthropic · $0.4412 / 1M tokens

Gemini 3.8 Flash

Google · $0.0551 / 1M tokens

DeepSeek V4

DeepSeek · $0.0613 / 1M tokens

The full list is in the model catalogue and the use-case collections.

Open WebUI + OpenLux questions

Does Open WebUI support OpenAI-compatible gateways?

Yes. The OpenAI connection type accepts any base URL, which is exactly what OpenLux provides — one endpoint that serves every model in the catalogue.

Which models should I enable first?

GPT-6 Astra as the quality default, Gemini 3.8 Flash for cheap high-volume chat and DeepSeek V4 when reasoning per dollar matters most. All are one entry in the model list.

Where does the API key live?

In the connection settings or as an environment variable. Keys can be rotated from the OpenLux console at any time without touching the UI configuration.

Can I run Open WebUI fully self-hosted on OpenLux?

Yes. Open WebUI runs on your own hardware and OpenLux is a plain HTTPS API, so the only traffic leaving your machine is the model calls themselves.

Connect Open WebUI to OpenLux today

One key covers every model in this guide and the rest of the catalogue, metered in USD with free trial credit to start.

Create an API key See pricing