Unzensierte API Documentation

Quickstart: send your first request

The Unzensierte API is an OpenAI-compatible service. You pay per token for text generation without content filters. Send a POST request to the chat completions endpoint with your API key. The model processes your prompt and returns text output directly.

Start by authenticating with your key. Then define the model ID as "uncensored". Specify your messages array with a role and content. The server responds with generated text. This works with any standard HTTP client or SDK. You get raw text, no extra formatting overhead. Errors return JSON with an error code. Use this quick path to verify your setup before building complex applications.

Authentication and base URL

Authentication uses a single API key passed in the header. The base URL is HTTPS://api.unzensierte.cc/v1. This URL works with official OpenAI SDKs by setting the base_url parameter. Your key identifies your account and tracks token usage. Generate a key on the Get API key page. It appears immediately after signup via Google or email. Use this key in every request. Invalid keys return a 401 error. Expired or insufficient credit returns 402.

Keep your key secure. One active key per account. A new key replaces the old one. No phone number is required for signup. The API key is the only credential needed for access.

Chat Completions endpoint

The core endpoint is POST /v1/chat/completions. It accepts JSON payloads with model, messages, and parameters. The model ID is "uncensored". Messages require a role and content string. The system responds with generated text in the choices array. You can set temperature, top_p, and stop sequences. These parameters control creativity and output length. The API returns token usage in the response. Errors include a message and type. Use this endpoint for all text generation tasks. It is the only text endpoint available. No embeddings or image generation here.

Streaming responses and usage

Enable streaming by setting stream to true. The API sends Server-Sent Events (SSE). Each chunk contains partial text. The final chunk includes token usage data. This allows real-time display of generated text. Buffer the chunks in your application. Combine them to form the complete response. Streaming reduces perceived latency for long outputs. Use this for chat interfaces or live data processing. The usage object appears only in the last chunk. Track input and output tokens for billing. Errors during streaming still return the error object in a chunk.

Function calling and JSON mode

Use function calling to integrate external tools. Define tools in the request body. The model returns tool calls with arguments. Parse these arguments to execute your functions. Set tool_choice to auto or specific function names. JSON mode forces the output to valid JSON. Set response_format to json_object. This ensures structured data for parsing. Use these features for automated workflows. Combine them for complex agent behaviors. The model supports standard OpenAI tool formats. Verify your tool definitions match the expected schema.

Limits and error handling

Rate limits are 300 requests per minute per key. Concurrency is limited to 8 simultaneous requests. Request bodies must be under 8 MB. Errors include specific codes like 401 for invalid keys. 402 indicates insufficient prepaid credit. 429 signals rate limit exceeded. Context window is 100,000 tokens total. Max output is 16,000 tokens per request. Errors return JSON with error details. Handle retries for 429 errors. Check credit balance before heavy usage. Refunds are not available for spent credit.

cURL

Copycurl https://api.unzensierte.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List 5 common Linux commands for file management"}]
  }'

Python

Copyfrom openai import OpenAI

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

Copyimport OpenAI from "openai";

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

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)