Connect your tools
Jan
The open-source desktop client: add a custom provider.
About 4 minFor:People who chat in Jan
Before you start
- Jan is installed
- A key and a model name
Step 1 · STEP 0x01
Add a custom provider
API format
Provider name
Go to Settings → Model Providers and click Add Provider. In the Add Custom Provider dialog set API format to OpenAI-compatible (or Anthropic-compatible for Claude-family models). The docs warn that the wrong format fails every request even with a correct URL and key.
Step 2 · STEP 0x02
Enter the Base URL and key
Base URL
API key
- The docs stress that the Base URL must include the version path your server expects, so enter
https://api.suanlimao.shop/v1with /v1. With Anthropic-compatible usehttps://api.suanlimao.shopwithout /v1. - Click Create.
Step 3 · STEP 0x03
Check the model list and chat
Model ID
Model picker in chat
- On save Jan fetches the model list from /models; our service supports it, so models normally appear automatically. If not, click + under Models and type the ID.
- Pick the model in chat and send a message.
✓ How to tell it worked
- Chat answers and the Usage page shows the request.
FAQ
404 on every request?
Per the official table: the Base URL is missing /v1 or the path is wrong.
401 / 403?
Bad or missing key.
Requests fail immediately?
Wrong API format (OpenAI-compatible and Anthropic-compatible swapped).
429?
Rate limited; wait and retry. If it persists, check the key's rate limit and open a ticket.
Related tutorials
Still stuck?
Read the troubleshooting tutorials first. If that does not help, open a ticket with the request_id, time, model and the exact error (never paste your key).