> ## 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.

# Cherry Studio

> Connect Cherry Studio to TokenLab with OpenAI-compatible and native endpoint options

## Overview

Cherry Studio can use TokenLab through a custom OpenAI-compatible provider. If your Cherry Studio version includes TokenLab in the provider registry, select TokenLab directly.

<Note>
  **Type**: Chat App

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

  **Native Paths**: Responses, Anthropic Messages, Gemini-compatible endpoints when exposed by the client
</Note>

## Configure as a Custom Provider

1. Open **Settings** -> **Model Provider**
2. Add an OpenAI-compatible provider
3. Enter:
   * **Name**: TokenLab
   * **API Base URL**: `https://api.tokenlab.sh/v1`
   * **API Key**: `sk-your-tokenlab-key`
4. Add a model such as `gpt-5.4-mini`
5. Save and test the provider.

## Provider Registry Path

When TokenLab appears as a built-in provider in Cherry Studio, prefer that option. It can carry endpoint metadata for:

* OpenAI-compatible chat completions
* OpenAI Responses
* Anthropic Messages
* Gemini generateContent

## Good Starter Models

Use `gpt-5.4-mini` for the default model, then add `claude-sonnet-5`, `gemini-3.5-flash`, and `deepseek-v4-flash` for broader coverage.