API Documentation & Quickstart

Authentication & Base URL

Start every request by pointing your client at HTTPS://api.uncensoredia.com/v1 and attaching your key. Authorization uses the standard Bearer scheme, so you simply paste the token you received after signing up with Google or email. The endpoint is fully openai compatible API compliant, meaning you only need to swap the base URL and API key in your existing configuration. You do not need to manage complex routing layers or proxy headers. Just ensure your Authorization header contains your unique token. This setup guarantees that your requests reach the dedicated uncensored model without any intermediate filtering. If you get a 401 error, verify that your key is active and correctly formatted.

Chat Completions Endpoint

Send messages to POST /v1/chat/completions to receive text responses from the uncensored model. This single endpoint handles all your generation needs, from simple prompts to complex multi-turn conversations. You can control the output length and randomness using parameters like max_tokens, temperature, and top_p. The model supports a massive 100,000 token context window, allowing you to feed in extensive documentation or long conversation histories. You can send up to 16,000 tokens in the response. If you omit max_tokens, the default limit is 2,048 tokens. This endpoint does not support image or audio generation. It is strictly text in, text out. Use the following curl command to test your connection immediately.

Python SDK Integration

Use the official OpenAI Python library to interact with the API with minimal code changes. You only need to override the base_url and api_key in the client configuration. This approach ensures that your existing logic for handling responses, errors, and retries remains intact. The library automatically handles JSON serialization and streaming if you enable it. This method is ideal for backend services or scripts that need to process large volumes of text. The uncensored model responds to standard chat completion requests without requiring custom parsing logic. Configure your client once and use it throughout your application. Here is how to initialize the client and send a basic request.

Node.js SDK Setup

Integrate the API into your JavaScript or TypeScript applications by using the @anthropic-ai/sdk or the official openai package. Set the baseURL to our endpoint and provide your API key. This allows you to use familiar methods like chat.completions.create() directly. The SDK handles the HTTP requests and parses the JSON responses for you. You can easily handle errors like 402 (insufficient credit) or 429 (rate limit) within your application logic. This setup is perfect for web servers, bots, or any Node.js environment. The uncensored model works seamlessly with the standard request format. Configure your client to ensure compatibility with the API's expectations.

Streaming Responses

Enable real-time token delivery by setting stream: true in your request. The API returns a Server-Sent Events (SSE) stream, allowing you to display text as it generates. This improves the user experience for chat interfaces and reduces perceived latency. Each chunk contains a partial response, and the final chunk includes the token usage statistics. You can process these chunks incrementally to build up the complete response. This feature is essential for applications that require immediate feedback. The uncensored model supports streaming for all request types. Handle the stream events to update your UI efficiently. Use this code to implement streaming in your client.

Rate Limits & Context Limits

The API enforces strict limits to ensure stable performance for all users. You can send up to 300 requests per minute per key and have 8 concurrent requests active at any time. The maximum request body size is 8 MB. If you exceed these limits, you will receive a 429 status code. Ensure you handle retries with exponential backoff to avoid hitting these limits repeatedly. The context window is 100,000 tokens, but the maximum output is 16,000 tokens. If you need more output, adjust the max_tokens parameter. Errors like 401 (invalid key) and 402 (no credit) are immediate and do not consume your token allowance. Manage your quota carefully to avoid service interruptions during high-volume generation tasks.

cURL

Copycurl https://api.uncensoredia.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "return json with key status true"}]
  }'

Python

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.uncensoredia.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.js

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.uncensoredia.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

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)