> ## 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.

# Jan

> Use TokenLab models in Jan through a remote OpenAI-compatible provider

## Overview

Jan can connect to TokenLab as a remote OpenAI-compatible provider.

<Note>
  **Type**: Chat App

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

  **Support Confidence**: Supported path
</Note>

## Configure Jan

1. Open **Settings** -> **Providers**
2. Add a remote OpenAI-compatible provider
3. Enter:
   * **Name**: TokenLab
   * **Base URL**: `https://api.tokenlab.sh/v1`
   * **API Key**: `sk-your-tokenlab-key`
4. Add or select `gpt-5.4-mini`
5. Save and start a new thread.

## Model Discovery

TokenLab exposes model discovery at:

```text theme={null}
https://api.tokenlab.sh/v1/models
```

If your Jan build supports remote model discovery for TokenLab, refresh the model list. Otherwise, add model ids manually.

## Recommended Models

* `gpt-5.4-mini`
* `gpt-5.4`
* `claude-sonnet-5`
* `gemini-3.5-flash`
* `deepseek-v4-flash`