Quickstart for Cursor users

Base URL and Authentication

Configure your client to point at https://api.cursorapikey.com/v1. The service expects standard OpenAI authentication headers. Generate your key on the Get API key page; you will need it for every request. Use the model ID uncensored to access the single available model. This setup works with any OpenAI-compatible SDK or agent like Cursor, Claude Code, or GitHub Copilot custom endpoints.

First Request

Test connectivity with a simple chat completion. The endpoint supports standard request bodies. If you receive a 200 status, your configuration is correct. A 401 error indicates an invalid or missing key, while a 402 error means your prepaid credit is exhausted.

Copycurl https://api.cursorapikey.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'

Requests exceeding 8 MB or 300 requests per minute may return specific error codes. Check the rate limit section for details.

Python SDK Integration

Use the official OpenAI Python library. Set the base URL and API key in your client initialization. The model ID remains uncensored. This approach works for local scripts or agent integrations that require programmatic API access. Ensure your library version supports the required OpenAI API structures.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.cursorapikey.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Remember that prompts are not used for training. Your code context remains private to the request.

Node SDK Integration

Initialize the OpenAI Node.js client with the custom base URL. Pass the API key from your environment variables. The model ID uncensored is required for all completions. This setup is ideal for Node-based agents or serverless functions requiring consistent AI assistance.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.cursorapikey.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

Verify your credentials before making bulk requests to avoid unnecessary 402 errors.

Streaming Responses

Enable streaming by setting stream: true in your request body. The API returns Server-Sent Events (SSE). This allows your UI or agent to process tokens as they are generated. Streaming reduces perceived latency for large responses. Ensure your client handles partial chunks correctly.

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Each chunk contains partial content. Aggregate these to form the final response.

Limits, Errors, and Context

The context window is 100,000 tokens for prompt and completion combined. Rate limits are 300 requests per minute per key. If you regenerate your key, the old one is revoked immediately. A 401 error indicates an invalid key. A 402 error indicates insufficient credit. A 429 error indicates rate limit exceeded. Credit never expires. Top-up options include crypto (USDT or USDC).