Uncensored LLM API for Developers

Copiarcurl https://api.llmsincensura.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."}]
  }'

Copiarfrom openai import OpenAI

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

Copiarimport OpenAI from "openai";

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

OpenAI Compatible API

Integrating uncensored llm into your current workflow is immediate. Our API follows the OpenAI chat-completions standard, meaning you only need to change the base_url and provide your API key. We support streaming via Server-Sent Events (SSE) and function calling to enrich your applications.

The model is identified by the ID uncensored. It is an open-weight model running on our own GPU servers, designed specifically to deliver the raw text you request. Whether you seek adult, controversial, or creative content, the model responds without the typical refusals of commercial models. Note: We only offer text. No image, audio, or video generation is available on this endpoint.

Uncensored Tuned Model

Unlike major providers that apply aggressive safety filters, our model is tuned to drastically reduce 'Well, actually...' or 'As an AI model...' responses. This ensures you get the exact output the prompt generates, with no political, social, or sexual censorship.

The model is not GPT, Claude, Gemini, or any other vendor. It is our own implementation optimized for freedom of expression in the output. There is one strict limit: sexual content involving minors is blocked, but everything else, including consensual adult content, flows without restriction. For developers who need consistency in tone without interruptions from automatic moderation, this is the direct solution.

100k Context

The 100,000-token context window allows you to send extensive documents or long conversation histories in a single request. This is crucial for applications requiring long-term memory or large file processing. You can combine input text with complex instructions and receive the full response within the same context.

The request body limit is 8 MB, which covers most dense text use cases. If your application requires embeddings, image classification, or audio, this API is not suitable; you are looking for pure text. The 100k capacity ensures the model maintains narrative or technical coherence across complex interactions.

Who is this API NOT for?

This uncensored AI is not for you if you need regulatory compliance guarantees like HIPAA or SOC2, as we do not offer them. It is also not the solution if you need to generate images, video, or audio, as our infrastructure is dedicated exclusively to text processing. If you are looking for multiple models from different providers (such as GPT-4o, Claude 3.5, etc.) with automatic routing, here you will find a single model optimized to be uncensored.

It is ideal for developers who prefer simplicity: one endpoint, one model, no surprises. If your application depends on guaranteed global latency with enterprise SLAs or requires on-premise deployment, consider other options. Here we offer speed, freedom, and transparent pricing.