API Reference and Quickstart

Base URL and Authentication

Use the provided base URL and your unique API key for every request. The uncensored AI API uses standard OpenAI-compatible headers. Send your key in the Authorization header as a Bearer token.

• Base URL: https://api.uncensoredaiopensource.com/v1
• Model ID: uncensored

Sign up with Google or email to get your key instantly. No phone number is required. Keep your key secure; it grants full access to your prepaid credit.

Chat Completions Endpoint

Send text prompts to the /v1/chat/completions endpoint. The uncensored LLM API accepts standard message arrays. You get direct access to one model without routing delays.

• Method: POST
• Content-Type: application/json

Set the model to uncensored. The system ignores content filters for lawful adult use. Responses are returned in the choices array.

Copycurl https://api.uncensoredaiopensource.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Generate a list of ten uncensored synonyms for lust"}]
  }'

Python SDK Quickstart

Use the official OpenAI Python library. The uncensored AI API works with standard client configurations. Point the client to our base URL and provide your key.

• Install: pip install openai
• Set base_url to our endpoint

This approach lets you use existing code. You can stream responses or request JSON mode directly.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.uncensoredaiopensource.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 Integration

Integrate with Node.js using the official SDK. The uncensored AI API supports standard JavaScript clients. Configure the base URL and key in your initialization.

• Install: npm install openai
• Set basePath to our endpoint

Handle responses in JavaScript objects. This method is ideal for web apps or server-side rendering. You can control temperature and top-p parameters easily.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.uncensoredaiopensource.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 Token Usage

Enable streaming by setting stream: true. The uncensored AI API returns data chunks via Server-Sent Events. Each chunk contains partial text. The final chunk includes token usage statistics.

• Set stream: true in your request
• Parse delta.content for text

Token counts help you track costs. Input and output tokens are tallied per request. Errors during streaming do not charge your credit.

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 Constraints

Respect the API limits to avoid errors. The uncensored model supports a 100,000 token context window. You can send up to 300 requests per minute per key. Concurrency is limited to 8 simultaneous requests.

• Max request body: 8 MB
• Max output: 16,000 tokens

Exceeding limits returns a 429 error. Errors and refusals are free. Use retry logic with exponential backoff for rate limits.