Set up Cherry Studio
Popular desktop AI client with one-click import; chat right after setup
- API format: OpenAI Chat Completions
- Base URL format: Domain only (https://gpt.cherrychat.org)
- Recommended model: gpt-6.1-sol, claude-sonnet-5-5
- Platforms: macOS, Windows, Linux
Steps
Fastest: one-click import
With Cherry Studio installed, click "One-click import" at the top of this page. Allow the browser to open Cherry Studio, confirm the dialog after checking it comes from CherryChat, and the provider and key are filled in. Then continue at step 4. If it is not installed or the import fails, follow step 2.
Add the provider manually
Fill in the API key and API address
Fill in the two fields on the new provider page. The preview under the address should then show https://gpt.cherrychat.org/v1/chat/completions.
Add models
- Model ID: gpt-6.1-sol
Check and enable
Common pitfalls
- Enter the domain only; Cherry Studio appends /v1/chat/completions. Entering https://gpt.cherrychat.org/v1/chat/completions doubles the path.
- A trailing # means "do not add the version path": https://gpt.cherrychat.org# loses /v1 and returns 404, so leave the # out.
- Turn on the provider switch at the top right, or its models will not appear in the chat model list.
- Separate multiple keys with English commas (they rotate); no Chinese commas and no surrounding spaces.
- The one-click link contains your key, so do not share it. Import needs a recent Cherry Studio (2.x); fill in older versions manually.
Error → cause → fix
| What you see | Why | What to do |
|---|---|---|
| Check fails with 401 | The API key is wrong, has spaces, or was disabled | Copy the key again from My Keys on the API page and paste it |
| Check fails with 404 | The API address is https://gpt.cherrychat.org/v1/chat/completions or ends with # | Change it to https://gpt.cherrychat.org and make sure the preview shows https://gpt.cherrychat.org/v1/chat/completions |
| Model not found when chatting | A manually added model ID is misspelled (case or spaces) | Remove it and add it again via Sync models, or copy the name from the Models page |
| HTTP 402 or "insufficient balance" (billing_error in Claude format) | Your credits cannot cover this call. API calls are paid from credits only; memberships and unlimited plans do not apply | Top up any amount in the CherryChat Store, then retry after a few seconds |
| HTTP 429 Too Many Requests | Too many requests: by default 120 per minute per key and 8 at a time per account | Lower the concurrency or requests per second in the tool and wait for the Retry-After seconds; most tools retry on their own |
Guide checked 2026-11-02. The tool's screens may change; the official docs win if they differ.
Operated by UK Company CHERRYCHAT LTD · Company Number 16096119 · Support WeChat: JsnonoChat · Content is AI-generated — please verify before relying on it
