BeansAI
ModelsPricingDocs
Sign inSign up
ModelsPricingDocs
Sign inSign up

Quickstart

  • Overview

Clients

  • Claude Code
  • CC Switch
  • OpenClaw
  • Roo Code
  • OpenCode
  • Codex CLI
  • GPT Image 2
  • Seedance 2.0
  • SkyReels V4
  • Mureka Song
  • Cursor
  • Cherry Studio

Reference

  • Raw API
← Back to Docs

Cherry Studio

Cross-platform desktop chat app. Add BeansAI as a new provider in three clicks.

Overview

Cherry Studio treats every provider as an OpenAI-compatible endpoint. Paste the BeansAI base URL and your key; model IDs auto-populate from the provider's model list.

Installation

Download from cherry-ai.com. Installers are available for macOS, Windows, and Linux.

Configuration

  1. Open Settings → Model Providers → Add.
  2. Choose OpenAI as the provider type, name it BeansAI.
  3. Fill in the values below.
Cherry Studio settings
API Host:   https://api.beansai.dev/v1
API Key:    sk-beans-...
API Path:   /chat/completions

Models to add:
  - gpt-5.5
  - gpt-5.1
  - gpt-5.2
  - gpt-5.3-codex-spark
  - claude-opus-4-7
  - claude-sonnet-4-6
  - gemini-2.5-pro
  - deepseek-chat

Basic usage

Create a new assistant, pick BeansAI as the provider, select a model. Streaming, tool calling, and vision inputs all work if the underlying model supports them.

Tips

  • Click Fetch Models to pull the live catalog from BeansAI instead of typing IDs manually.
  • For Claude models, set the Max Tokens per-assistant to 64000 to unlock the full output window.
  • Cherry Studio supports multiple providers — keep BeansAI alongside direct OpenAI/Anthropic for A/B testing.