API Documentation

Authentication and base URL

Start every request with your API key in the Authorization header. Our base URL points directly to the chat-completions endpoint, so you can swap in your key and go.

Get a key instantly via Google or email. The key appears on screen immediately, no phone number required, and you can generate a new one to replace the old one at any time.

Keep your key private. Each account holds one active key, and errors or refusals do not consume your prepaid credit.

First request

Send a POST request to the chat endpoint with your model id set to uncensored. This simple structure works with any OpenAI-compatible client.

• Set the Authorization header to Bearer YOUR_API_KEY.
• Target the endpoint at our base URL.
• Include your messages array and model identifier.

Text goes in, text comes out. No extra configuration is needed for basic usage.

Copycurl https://api.aiunrestricted.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "What is the capital of France"}]
  }'

Python SDK integration

Initialize the OpenAI client with our base URL and your key. The Python SDK handles serialization automatically, letting you focus on your logic.

Pass the model id uncensored to ensure you are hitting our specific inference layer. This guarantees consistent uncensored behavior across all generations.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.aiunrestricted.cc/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 integration

Configure the Node.js client to point at our API. This approach works well for bots or serverless functions that need rapid integration.

Set the apiKey and baseURL properties correctly. The SDK manages the HTTP calls, so you just await the response.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.aiunrestricted.cc/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 responses

Enable streaming by setting stream to true in your request body. You will receive Server-Sent Events (SSE) as tokens are generated.

Parse the chunks to display text in real time. The final chunk contains the token usage statistics, so you can track costs accurately without extra calls.

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)

Rate limits and error handling

Expect a 401 if your key is invalid, a 402 if your prepaid credit is exhausted, and a 429 when you hit the rate limit of 300 requests per minute per key.

You can run 8 concurrent requests simultaneously. Request bodies must stay under 8 MB. Handle these errors gracefully by retrying with exponential backoff or prompting for a top-up.

The context window supports 100,000 tokens for the prompt and completion combined, allowing for deep context retention in your applications.