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

# Open WebUI

> Use TokenLab as an OpenAI-compatible API connection in Open WebUI

## Overview

Open WebUI supports custom OpenAI-compatible API connections. Add TokenLab as a remote OpenAI-compatible endpoint and refresh the model list.

<Note>
  **Type**: Web Chat App

  **Primary Path**: OpenAI-compatible chat completions

  **Support Confidence**: Supported chat-app path
</Note>

## Admin Connection

1. Open **Admin Panel** -> **Settings** -> **Connections**.
2. In the OpenAI API connection area, add a connection.
3. Set the base URL to `https://api.tokenlab.sh/v1`.
4. Set the API key to your TokenLab key.
5. Save the connection and refresh models.

## Values

| Field         | Value                        |
| ------------- | ---------------------------- |
| API Base URL  | `https://api.tokenlab.sh/v1` |
| API Key       | `sk-your-tokenlab-key`       |
| Example model | `gpt-5.4-mini`               |

## Recommended Models

* `gpt-5.4-mini` for general chat
* `claude-sonnet-5` for writing and reasoning
* `deepseek-v4-pro` for code-heavy chat
* `gemini-3.5-flash` for fast multimodal-friendly workflows

If model discovery is disabled or cached in your deployment, add the model IDs manually in Open WebUI's model settings.