Connecting Cherry Studio

Difficulty 🖱️ Easy (all mouse clicks, zero code)　|　API format OpenAI compatible　|　base_url https://byesu.com/v1

Setup · fill these in

API addresshttps://byesu.com/v1

API keysk-xxxxxxxxCreate in console →

Modelgpt-5.5

API format OpenAI compatible · model names follow the console

Cherry Studio is a free desktop AI client that requires no coding at all. Point it at byesu — an AI API gateway with OpenAI-compatible and Anthropic-native endpoints — and one key lets you chat, write, and process documents with Claude, GPT-5.6, Grok, Gemini and more, billed pay-as-you-go with no subscription.

Before you begin

First, go to Console → Tokens and create an API Key (if you're not sure how, see Quick Start). Have a Key that looks like sk-xxxx ready before continuing.

Step 1: Download and install

Open the official site cherry-ai.com, download the version for your computer (Windows or macOS), then install and open it just like any ordinary program.

Step 2: Add "byesu" as a provider

1. Click Settings in the bottom-left corner (the gear icon ⚙️).
2. Find Model Service / Model Provider, click Add, and choose OpenAI as the type.
3. Fill in two things:
   • API Host: enter https://byesu.com
   • API Key: paste your sk-xxxx

After entering the address, check this

Cherry usually shows a preview of the actual request address below. Confirm that it reads https://byesu.com/v1/chat/completions. If it turns into …/v1/v1/…, just remove the extra /v1 you added at the end of the address.

Cherry Studio uses the OpenAI-compatible endpoint (https://byesu.com/v1). byesu also exposes an Anthropic-native /v1/messages endpoint for clients like Claude Code — see Claude Code CLI Setup.

Step 3: Add the models you want to use

Under this provider, click Manage / Add Model and type in the model name — the name must be exactly identical to what's listed in the Console (case and dashes must all match).

Want the best results? Just enter the top flagship from each platform: gpt-5.5, claude-opus-4-8, gemini-3.1-pro-high, grok-420-fast, a/glm-5.2 (see the full list in the Console).

Step 4: Start using it ✅

Go back to the chat screen, select the model you just added at the top, and send a "hello". If it replies, you're connected!

How billing works

Billing is pay-as-you-go per token — no subscription, no monthly plan. Each model's price is expressed as a multiplier relative to its official list price, and the Console shows your live billed price next to the official list price. Top up with USDT or Alipay.

Stuck?

• 401 / Invalid token → the Key is wrong or has leading/trailing spaces (details)
• 404 / Wrong endpoint → check whether the "address preview" in Step 2 reads /v1/chat/completions
• Insufficient balance → top up in the Console (details)
• No available channel → the model name is wrong or not in your group (details)
• For others, see Common Errors