Uncensored API Quick Start Guide

Installation and Required Libraries

The uncensored API is designed to work directly with OpenAI SDKs and clients. To set up integration, you only need to set the base_url value in your existing code to https://api.sansursuzapi.com/v1 and configure your API key. You just need to install the appropriate SDK package for your language; no additional server configuration or complex authentication mechanisms are required. Our system uses standard Bearer token authentication and we pass your key directly in the request headers.

Basic Request Example

To start using the API, you can trigger text generation by sending a simple POST request. The example below shows how to access the curl uncensored model. The request body specifies the model name, user message, and response format. This structure conforms to OpenAI's standard chat-completions schema.

Kopyalacurl https://api.sansursuzapi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'

This request is an ideal starting point to test the model's uncensored behavior. The JSON object returned as a response contains the generated text and token statistics. You can use this simple structure for quick tests, then customize parameters according to your project's needs.

Streaming and Function Calling

For large text blocks or long conversation history scenarios, you can use streaming mode. This mode allows you to process data from the server in parts and improves user experience. Additionally, the function calling feature, which allows the model to interact with external tools, is supported. This feature allows the model to return data according to a specific JSON schema and process this data in your application.

Kopyalafrom openai import OpenAI

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

Kopyalaimport OpenAI from "openai";

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

Python and Node.js SDKs provide the necessary tools to manage these streaming and function structures. Optionally, you can receive the response in parts with the stream: true parameter or configure the model's data generation using the tools structure.

Model List and Compatibility

Our API currently offers a single large language model: uncensored. This model has a custom-tuned open-weight architecture and is optimized to remove the artificial filtering seen in standard models. You can verify the available model via the model list endpoint (GET /v1/models). The model runs on our GPU servers, independent of OpenAI's GPT, Claude, Gemini, or Grok series. This compatibility allows you to use your existing OpenAI clients directly.

Error Codes and Limits

The main status codes you may encounter while using the API are: 401 for invalid or missing API key, 402 for insufficient credit, and 429 for exceeding the rate limit of 300 requests per minute. Only one API key is valid per account; when the key is regenerated, the old key becomes inactive. The request body should not exceed 8 MB. The context window is limited to 100,000 tokens; this refers to the total number of tokens for both prompt and completion text. These limits are critical for the stable operation of the API.

Pricing and Credit Management

The uncensored API works on a pay as you go model. Input tokens are charged at $0.25 per 1 million tokens, and output tokens at $1.00 per 1 million tokens. Paid credit is stored indefinitely and there is no subscription fee. New accounts receive $0.50 in free trial credit valid for 7 days without requiring a credit card. When credit runs out, the service does not stop; you only need to top up for new requests. A 5% bonus applies to $50 top-ups and a 10% bonus applies to $100 top-ups.

Streaming

Kopyalastream = 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)