# Cherry Studio

> Configure Cherry Studio with a ScaleMax key, compatible base URL, exact model ID, and a minimal verification request.

## Connection settings

- **Provider:** OpenAI Compatible / Custom OpenAI provider
- **API-credit base URL:** `https://api.scalemax.pro/v1`
- **Token-pack base URL:** `https://api.scalemax.pro/token/v1`
- **API key:** your full ScaleMax key
- **Model:** an exact ID returned by the authenticated `/models` endpoint (for example, `fable-5` for a Claude-capable or both-scope key)

Fable 5 is an Anthropic-family frontend model. A Claude-only or both-scope key can use the same OpenAI-compatible provider form and matching `/v1` URL, but Fable never appears for an OpenAI-only key.

## Models

- `fable-5`
- `gpt-6.1-sol`
- `gpt-6-sol`
- `gpt-6-luna`
- `gpt-6-astra`
- `gpt-5.6-terra`
- `gpt-5.6-sol`
- `gpt-5.6-luna`

## Provider settings

Open model provider settings, choose OpenAI/OpenAI-compatible, use the URL that belongs to the key, add only models returned by that key's catalog, and save.

## Automatic setup

**macOS / Linux**

```bash
npm install -g scalemax@latest
scalemax
```

**Windows PowerShell**

```powershell
npm.cmd install -g scalemax@latest
scalemax.cmd
```

Windows PowerShell blocks npm’s .ps1 launchers by default (“running scripts is disabled on this system”), so these commands use the .cmd launcher: npx.cmd, npm.cmd, scalemax.cmd. In Command Prompt you can leave out .cmd.

The installer writes a setup guide with the base URL detected from the key under `~/.scalemax/`.