Set up Cursor and other OpenAI-compatible tools

Any tool that accepts a custom OpenAI-compatible provider works with AIFans API. You need three things: the base URL, an API key and a model name.

Base URL

https://api.aifans.fan/v1

API key

Create one in the console; it starts with sk-

Model

For example deepseek-v4.1-flash; the full list is on Models and prices

Cursor

1. Open Settings → Models and paste your key into the OpenAI API Key field.
2. Turn on “Override OpenAI Base URL” and enter https://api.aifans.fan/v1.
3. Add a custom model with the model name (e.g. deepseek-v4.1-flash) and enable it.

Menu names change between Cursor versions; follow what you see.

Other tools and SDKs

Cline, Continue, OpenCode, Dify, LangChain and more have their own step-by-step pages under Guides. Anything else works the same way: point the base URL at https://api.aifans.fan/v1 and use your key and a model name.

curl https://api.aifans.fan/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "deepseek-v4.1-flash", "messages": [{"role": "user", "content": "Hello"}], "max_tokens": 1000}'

Tips

• Use a separate key per tool and per machine, with a spending limit, so you can disable just the one that misbehaves.
• If a tool runs on a server with a fixed IP, add an IP allow-list to its key.
• Use a max_tokens of 1000 or more; the API reference explains why.