---
title: "Open WebUI with EU-hosted models · Connection setup"
description: "Connect Open WebUI to inference.eu as an OpenAI-compatible connection and give your team a self-hosted chat on open-weight models processed in the EU."
canonical: "https://inference.eu/integrations/open-webui/"
language: "en"
---

Chat apps · Open WebUI

# Use Open WebUI with open-source models hosted in the EU

Open WebUI is a self-hosted chat interface with users, groups, document chat and tools. Add inference.eu as an OpenAI-compatible connection and your team gets a familiar chat experience on open-weight models processed in European data centres, on infrastructure you control.

[Contact sales](https://inference.eu/contact/)[Setup](#setup)

1.  01API format: OpenAI
2.  02EU data centres
3.  03Covered by one DPA

## Set it up in a few minutes

1.  1

    Create an API key in your inference.eu account.

2.  2

    In Open WebUI, go to Settings > Admin > Connections and click Add Connection under the OpenAI API connections.

3.  3

    Enter the inference.eu base URL and your API key, then click Verify Connection.

4.  4

    Leave Model IDs empty to load all models, or add the ids you want to offer, such as `gpt-oss-120b`, and save.

5.  5

    Open a new chat, select an inference.eu model and send a message to confirm it works.

bash

```
docker run -d --name open-webui -p 3000:8080 \
  -v open-webui:/app/backend/data \
  -e OPENAI_API_BASE_URLS="https://api.inference.eu/v1" \
  -e OPENAI_API_KEYS="$INFERENCE_EU_API_KEY" \
  -e ENABLE_OLLAMA_API=false \
  ghcr.io/open-webui/open-webui:main

# Or in the UI: Settings > Admin > Connections > Add Connection,
# with the inference.eu base URL and your API key.
```

## What Open WebUI is

Open WebUI is an open-source web interface for language models that you run yourself, usually with Docker or Kubernetes. It offers a chat experience similar to commercial assistants, plus user management with roles and groups, document upload and knowledge bases, web search, tools, prompts and model presets that admins can share across the organisation.

It connects to models through OpenAI-compatible connections. Any number of connections can be added, each with its own URL, key and model list. inference.eu works as one of these connections, so models appear in the model picker for the users and groups you allow.

## How the configuration works

In Settings > Admin > Connections, add a connection with the inference.eu base URL ending in `/v1` and your API key. Open WebUI calls `/models` to discover the available models; you can restrict the list with Model IDs. Each connection can be enabled or disabled without losing its settings.

For automated deployments, set `OPENAI_API_BASE_URLS` and `OPENAI_API_KEYS` as environment variables, separating multiple connections with semicolons in matching order. Open WebUI stores these values in its database on first start; after that, changes made in the admin panel take precedence over the environment unless you disable persistent configuration.

## Which models to choose

For general chat, writing and summarising, `gpt-oss-120b` gives quick answers that keep the interface responsive. For document chat over long files and questions that need careful reasoning, `glm-5.3` and `kimi-k3` are strong choices. Teams that ask coding questions benefit from `qwen3-coder-480b-a35b-instruct`.

Admins can create workspace models on top of these, with a system prompt, attached knowledge and tools, and share them with specific groups. Set the function calling mode to native for models with dependable tool calling, so tools run through the model's own tool calls rather than prompt-based detection.

## Troubleshooting

If Verify Connection fails with 401, the key is wrong or has a trailing space. A 404 usually means the URL is missing `/v1` or has an extra path. If no models appear, check the Model IDs filter and that the connection is enabled.

If a change to `OPENAI_API_BASE_URLS` has no effect after a restart, the value saved in the database is being used; update the connection in the admin panel instead. If Docker cannot reach the URL, check the container's outbound network and proxy settings. If tools are not called, switch the model's function calling mode or choose a model with stronger tool support.

## Keeping data in the EU

With inference.eu as the connection, every chat message, uploaded document excerpt and tool result sent to the model is processed in EU data centres and never used for training. We sign a data processing agreement under Article 28 GDPR, publish our subprocessor list and bill in euros.

Open WebUI stores chats, files and users in its own database, so host it in the EU. Web search, image generation, speech and embedding settings can each use a separate provider; configure EU-hosted or local options for them, and disable or remove connections you do not want users to reach.

## Open WebUI

Category

Chat apps

Maker

Open WebUI

API format

OpenAI

Processing

EU data centres

Website

[openwebui.com](https://openwebui.com/)

Documentation

[docs.openwebui.com](https://docs.openwebui.com/getting-started/quick-start/connect-a-provider/starting-with-openai-compatible)

## Open WebUI: common questions

The questions buyers, developers and legal teams ask us most. Something missing? Ask us directly.

Go to Settings > Admin > Connections, click Add Connection under the OpenAI API connections, and enter the base URL and API key. Verify the connection, optionally list the Model IDs to offer, and save. The models then appear in the chat model picker.

Yes. Set \`OPENAI\_API\_BASE\_URLS\` to the inference.eu base URL and \`OPENAI\_API\_KEYS\` to your key, using semicolons for multiple connections. These values are saved on first start, so later changes should be made in the admin panel.

Open WebUI saves many settings to its database on first start and then prefers the stored values. Edit the connection under Settings > Admin > Connections, or disable persistent configuration if you want environment variables to win on every restart.

gpt-oss-120b is a quick default for everyday chat. GLM-5.3 and Kimi K3 suit document chat and careful reasoning, and Qwen3 Coder 480B is a good model for teams asking coding questions. You can offer several and let users choose.

Yes. Model visibility can be set per model, and workspace models can be shared with specific groups. Combine this with the Model IDs list on the connection to control exactly which inference.eu models each team can use.

Yes. Uploaded files and knowledge bases are retrieved by Open WebUI and passed to the model as context. Choose a model with a large context window, such as GLM-5.3 or Kimi K3, for long documents.

Yes. For models with dependable tool calling, set the function calling mode to native in the model's advanced parameters. Open WebUI then sends tools in the standard format and runs them when the model calls them.

A 401 means the key is wrong or has extra whitespace. A 404 means the URL is missing \`/v1\` or includes an extra path. A timeout points to network or proxy settings on the server running Open WebUI.

Open WebUI stores chats in its own database. Features such as web search, image generation, speech and embeddings use the providers you configure for them. Review each setting and choose EU-hosted or local options to keep data in Europe.

Yes. Add inference.eu as an OpenAI connection and keep local models through an Ollama or other connection. Users then pick the model per chat. Disable connections you do not need so models are not offered by mistake.

[Ask a question](https://inference.eu/contact/)

## Related

[All integrations](https://inference.eu/integrations/)

-   [LibreChatAdd inference.eu as a custom endpoint in librechat.yaml and give your organisation a self-hosted chat with agents on open-weight models processed in the EU.Chat apps](https://inference.eu/integrations/librechat/)
-   [AnythingLLMConnect AnythingLLM to inference.eu with the Generic OpenAI provider and chat with your documents using open-weight models processed in the EU.Chat apps](https://inference.eu/integrations/anythingllm/)
-   [LiteLLMAdd inference.eu to the LiteLLM proxy or Python SDK with the openai/ prefix and route your team's requests to open-weight models processed in the EU.Gateways](https://inference.eu/integrations/litellm/)

## Move your AI workloads to EU infrastructure

Tell us which models you use and roughly how much traffic you have. We reply within one working day with pricing and next steps.

-   Reply within one working day
-   Pricing for your volume
-   DPA ready to sign