API Documentation for Cursor Developers

Authentication and Base URL

Our API uses standard Bearer token authentication. Set your base URL to HTTPS://api.cursoraiapikey.com/v1 and pass your key in the Authorization header. This endpoint works with any OpenAI-compatible SDK. You get a key immediately after signing up with Google or email. No phone number is required. Credit never expires. Errors are free. Refusals are free. Pay only for real tokens. Authorization: Bearer YOUR_API_KEY is all you need. Start making requests right away. The system is simple. Transparency matters.

First Request

Send a POST request to /v1/chat/completions to generate text. Use model "uncensored" for unrestricted responses. Include your system prompt to guide behavior. The API accepts standard OpenAI JSON structures. Here is a basic example using curl. Replace YOUR_API_KEY with your credential. Send your message and receive text output. This is the core interaction. Keep it simple.

Copycurl https://api.cursoraiapikey.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List three key features of the new API update"}]
  }'

Python SDK Integration

Use the official OpenAI Python package. Set the base URL and API key. Pass messages as a list of dictionaries. Request the "uncensored" model. The SDK handles retries automatically. Streaming is supported. Function calling works too. Configure temperature and top_p for control. This approach minimizes code changes. Your existing logic stays intact. Just point to our URL. Efficiency is key. Developers prefer familiar tools.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.cursoraiapikey.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)

Node SDK Usage

Initialize the OpenAI client in Node.js. Override the basePath to our URL. Set apiKey to your credential. Call chat.completions.create(). Pass the model as "uncensored". Await the result. Handle errors gracefully. The Node ecosystem is robust. You get real-time responses. Code is clean. Dependencies are standard. No extra libraries needed. Just configure the client. Run your script. Get your text. Simplicity wins.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.cursoraiapikey.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);

Streaming and Tool Support

Enable streaming by setting stream to true. Receive tokens via Server-Sent Events. Use function calling for tool integration. Define tools in your request. The model returns arguments. Parse them safely. Support for JSON mode exists. Set response_format to json_object. This ensures valid output. Combine streaming with tools for dynamic apps. Real-time updates improve UX. Developers love low latency. Control the flow. Adapt to needs. Flexibility is essential.

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)

Limits, Errors, and Context

Context window is 100,000 tokens. Max output is 16,000 tokens. Requests per minute limit is 300. Concurrent requests per key is 8. Max body size is 8 MB. Error 401 means invalid key. Error 402 means no credit. Error 429 means rate limit. Credit is prepaid. Errors are free. Refusals are free. No monthly fees. Use crypto to top up. USDT or USDC. Start with $20. Get bonuses. Keep coding.