Uncensored API Documentation

Authentication & Base URL

Start by generating your key on the dashboard. You authenticate using a Bearer token in the Authorization header. The base URL for all requests is https://api.censuresansia.com/v1. This setup works with any standard OpenAI SDK because we follow the same interface conventions.

• Sign up with Google or email.
• Copy your API key immediately.
• Set the base URL in your client configuration.

POST /v1/chat/completions

Send your first completion request using the standard chat endpoint. You must specify the model uncensored to ensure you get the unfiltered response. Input and output tokens are billed separately at $0.15 and $0.50 per million tokens respectively.

Copycurl https://api.censuresansia.com/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?"}]
  }'

This request demonstrates a simple text generation. The model responds without the typical gatekeeping found in other providers. You receive a direct text output ready for your application logic.

Python SDK Integration

Use the official OpenAI Python library to interact with our API. Set the base_url and api_key before initializing the client. This approach keeps your code compatible with existing OpenAI patterns while removing content restrictions.

Copyfrom openai import OpenAI

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

The code snippet initializes the client correctly. It sends a message and prints the response. This method is reliable for backend services that need consistent text generation without manual HTTP handling.

Node SDK Integration

Integrate with Node.js using the official npm package. Configure the client with your base URL and key. This allows you to build server-side applications that generate text instantly. The model handles complex prompts efficiently.

Copyimport OpenAI from "openai";

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

The example shows how to create a client instance. It then calls the chat completion method. You can parse the result directly into your application state. This setup ensures low latency for your users.

Streaming with SSE

Enable real-time text delivery by setting stream: true. The API returns a Server-Sent Events stream. You process each chunk as it arrives. This reduces perceived latency significantly for end-users. Token usage details appear in the final chunk.

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)

The streaming code handles the async iterator. It concatenates partial responses into a complete message. This technique is ideal for chat interfaces where typing effects matter. It keeps the connection open until the model finishes generating.

Rate Limits & Errors

You are limited to 300 requests per minute and 8 concurrent connections per key. If you exceed this, you receive a 429 error. A 401 error means your key is invalid. A 402 error indicates insufficient prepaid credit. The context window supports 100,000 tokens total.

Errors are free, so you do not pay for failed attempts. Keep your request bodies under 8 MB. Replace your API key if you need a fresh limit reset. This structure ensures predictable performance for your application.