Set up n8n
Open-source workflow automation. Change the Base URL in the OpenAI credential to use CherryChat
- API format: OpenAI Chat Completions
- Base URL format: Up to /v1 (https://gpt.cherrychat.org/v1)
- Recommended model: gpt-6.1-sol, deepseek-v4-flash
- Platforms: Web
Steps
Create an OpenAI credential
Open Credentials → Create credential (or "Create new credential" inside a node), choose "OpenAI", fill in the fields below, leave Organization ID empty and click Save. n8n tests the connection with this address.
- API Key: sk-your-key
- Base URL: https://gpt.cherrychat.org/v1 (Replace the default https://api.openai.com/v1 with this)
Use it in the OpenAI Chat Model node
Attach an "OpenAI Chat Model" sub-node to an AI Agent or Basic LLM Chain node. Pick the new credential, choose the model from the list or switch to "By ID" if it will not load, and keep "Use Responses API" off.
- Model (By ID): gpt-6.1-sol
Run a test
Click "Execute step" on the node or run the whole workflow; a model reply means it works.
Without AI nodes: HTTP Request
You can also use an HTTP Request node: Method POST, URL https://gpt.cherrychat.org/v1/chat/completions, Authentication "Generic Credential Type" → "Header Auth" (Name Authorization, Value Bearer, a space, then the key), turn on Send Body, choose JSON and paste the content below.
Common pitfalls
- Base URL ends at /v1 (https://gpt.cherrychat.org/v1); saving the credential tests https://gpt.cherrychat.org/v1/models.
- Keep "Use Responses API" off; it enables built-in tools such as Web Search, which CherryChat API does not support yet.
- On n8n Cloud, do not pick "Use Gateway credits"; that is n8n's own quota, not CherryChat.
- In HTTP Request nodes, store the key in a Header Auth credential rather than a plain header so exported workflows do not leak it.
Error → cause → fix
| What you see | Why | What to do |
|---|---|---|
| Couldn't connect / 401 when saving the credential | The key is wrong, has spaces, or was disabled | Copy the key again from My Keys and save again |
| HTTP 404 Not Found | Base URL is missing /v1, or the HTTP Request URL is not the full path | Credential: https://gpt.cherrychat.org/v1; HTTP Request: https://gpt.cherrychat.org/v1/chat/completions |
| The model list will not load, or model not found | The list failed to load, or the typed model name is wrong | Switch Model to "By ID" and enter gpt-6.1-sol 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
