Set up NextChat / LobeChat
Two popular open-source chat UIs. Fill in a custom endpoint, but note their address formats differ
- 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: Web, macOS, Windows
Steps
NextChat: enable the custom endpoint
Click the gear at the bottom left to open Settings, turn on "Custom Endpoint", choose OpenAI as the provider and fill in the two fields below. Use the domain only; NextChat adds /v1/chat/completions.
- Endpoint (NextChat): https://gpt.cherrychat.org (Domain only, without /v1)
- API Key: sk-your-key
NextChat: add the model name
On the same page, enter the model in "Custom Models" (separate several with English commas). Back in the chat, pick it from the model button above the input box.
- Custom Models: gpt-6.1-sol
LobeChat: add a custom provider
Go to Settings → AI Service Provider → "Add custom provider". Set the ID to cherrychat, the name to CherryChat, request format OpenAI, then the proxy address and API key, and click Create. Unlike NextChat, LobeChat needs /v1.
- Proxy address (LobeChat): https://gpt.cherrychat.org/v1 (LobeChat needs /v1)
- API Key: sk-your-key
LobeChat: check and add models
On the provider page, click Check under the connectivity check until it passes. Then fetch the model list and enable the models you want, or add a model with ID gpt-6.1-sol.
Common pitfalls
- The two differ: NextChat takes the domain only (https://gpt.cherrychat.org) and adds the path; LobeChat needs /v1 (https://gpt.cherrychat.org/v1).
- Never enter your key on someone else's public NextChat / LobeChat site; requests pass through their server. Use the official app or your own deployment.
- Avoid one-click links that put settings in the URL; the key ends up in browser history and server logs.
- Model names must match the Models page (lowercase); separate several NextChat models with English commas.
Error → cause → fix
| What you see | Why | What to do |
|---|---|---|
| HTTP 401 | The key is wrong, has spaces, or was disabled | Copy the key again from My Keys and paste it |
| NextChat returns 404 | The endpoint was set to https://gpt.cherrychat.org/v1, producing /v1/v1/… | Use the domain only: https://gpt.cherrychat.org |
| LobeChat check fails or the model list is empty | The proxy address is missing /v1 | Change it to https://gpt.cherrychat.org/v1 and check again |
| Model not found | The model name is misspelled (case or spaces) | Copy it from the Models page, e.g. gpt-6.1-sol |
| 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
