> ## Documentation Index
> Fetch the complete documentation index at: https://docs.scitix.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Open WebUI

[Open WebUI](https://github.com/open-webui/open-webui) is a self-hosted web interface for large language models. It talks to OpenAI-compatible backends, so you can point it to the ScitiX Model Inference API and chat with ScitiX models from a browser.

The steps below use Open WebUI v0.11.0. Newer versions may differ slightly. For available models, such as `glm-5.2` and `DeepSeek-V4-Flash`, and pricing, see the [model catalog](https://console.scitix.ai/model-inference/models).

## Configure

Create an API Key on the [API Keys](https://console.scitix.ai/model-inference/api_keys) page, then set two environment variables before starting the server:

```bash theme={null}
export OPENAI_API_BASE_URL="https://api.scitix.ai/model-api/v1"
export OPENAI_API_KEY="<Your API Key>"
open-webui serve --port 8080
```

| Variable              | Description                                                                                      |
| --------------------- | ------------------------------------------------------------------------------------------------ |
| `OPENAI_API_BASE_URL` | ScitiX OpenAI-compatible endpoint: `https://api.scitix.ai/model-api/v1`.                         |
| `OPENAI_API_KEY`      | Your API Key created on the [API Keys](https://console.scitix.ai/model-inference/api_keys) page. |

<Note>
  An `export` only lasts for the current shell session. Add the two lines to `~/.bashrc` or `~/.zshrc` to make them permanent.
</Note>

Open the printed URL, such as `http://localhost:8080`, and create the first account. The first account becomes the administrator.

With the two variables set, Open WebUI reads the model list from the ScitiX endpoint automatically. No per-model setup is needed.

Additional connections and per-model options live in **Admin Settings → Connections**. Choose a model with native tool calling if you rely on Open WebUI's tool/function features.

<img src="https://mintcdn.com/scitix-adfc65c2/_I6H7WpAVXPiLIwE/model-inference/media/openwebui-chat.png?fit=max&auto=format&n=_I6H7WpAVXPiLIwE&q=85&s=b637a56473c93d8289411e02f74922cc" alt="Open WebUI — a ScitiX model selected in the chat interface" width="2880" height="1800" data-path="model-inference/media/openwebui-chat.png" />

## Verify

Pick a ScitiX model from the model selector at the top of the chat and send a message. A normal reply confirms that the connection works.

## FAQ

* If the model picker is empty, confirm that the two variables were exported in the shell that launched `open-webui serve`, and that `GET https://api.scitix.ai/model-api/v1/models` returns a list with your key.
