Quickstart: Use Unzensiertes LLM API

Base URL and Authentication

unzensiertesllm.com's API follows established standards to simplify integration. All requests are sent to the base URL https://api.unzensiertesllm.com/v1. You need an API key, which you receive immediately after registration on the "Get API key" page. This key is passed in the Authorization: Bearer <IHR_SCHLÜSSEL> header. If you use the official SDKs, you can configure the base URL and API key in the OPENAI_API_KEY and OPENAI_BASE_URL environment variables. The model you call has the ID uncensored. It is a standalone, specially tuned model that does not belong to well-known major providers like GPT or Claude.

Send First Request

To test the functionality, send a simple chat request. The interface expects a JSON object with the role user and a message. The response type is text. A successful request returns a response in the standard format. If the API key is invalid, you get a 401 error. If your credit is exhausted, the API reports 402. For your first use, you receive $0.50 in trial credit, valid for seven days.

Kopierencurl https://api.unzensiertesllm.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."}]
  }'

Use Python SDK

Integration into Python projects is directly possible via the official openai package. Since the API is OpenAI-compatible, you can use the familiar syntax. Simply adjust the base_url and set the API key. The uncensored model processes inputs without the typical content filters of other providers, making it ideal for creative or adult content. Make sure to keep the library up to date to ensure compatibility.

Kopierenfrom openai import OpenAI

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

Developers working with JavaScript or TypeScript can use the openai NPM package. Configure the client instance with the base URL of our infrastructure. This enables seamless integration into existing web applications or backend services. The response is returned as a stream or as a complete object, depending on the configuration. The uncensored model also supports tool calls, facilitating use in complex workflows. Ensure your Node.js environment is modern to fully utilize all features.

Kopierenimport OpenAI from "openai";

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

Enable Streaming (SSE)

For real-time applications, streaming responses is essential. Set the parameter stream: true in your request. The API then sends Server-Sent Events (SSE) containing chunks of the generated text. This significantly improves perceived latency for end users. You can render the text incrementally while the model is still thinking. This is particularly useful for chat interfaces that require immediate feedback without waiting for full generation.

Kopierenstream = 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)

List Models and Limits

Use the endpoint GET /v1/models to query available models. You will see the model uncensored with its details. Pay attention to the rate limits: 300 requests per minute are allowed per key. The request body must not exceed 8 MB. The context window is 100,000 tokens (prompt plus response). If exceeded, you receive error codes such as 429. The API does not offer embeddings or image generation. It focuses purely on text completion. Prepaid credit never expires, and you can top up starting from $10.