API Quick Integration Guide

Authentication and Base URL

To consume our AI API, you will need an API key and the correct base URL. Sign in on the Get API key page with your email and password to get your key immediately; no card is required for the trial. Use the base URL https://api.llmsincensura.com/v1 with any OpenAI-compatible client. Authentication is done by sending your key in the Authorization: Bearer YOUR_API_KEY header. This standard method ensures your uncensored LLM works with the tools you already know.

The model you will serve is uncensored. Make sure to configure it in your requests. There are no complex routes; you send text and receive raw text. If your application requires a specific endpoint, this is the only one you need for chat. Simplicity is key for fast, frictionless integration.

Endpoint /v1/chat/completions

The core of the uncensored AI API is the chat completion endpoint. Send a list of messages (system, user, assistant) and receive a complete response. This direct approach avoids the content refusals common in other models for adult or controversial topics. The JSON structure is identical to OpenAI's, making it easy to switch if you come from another platform.

Remember that we only support this endpoint for text. There are no embeddings or image generation. To get started, you can test a simple request with curl to verify that your key works and that the response arrives unfiltered.

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."}]
  }'

Python Integration

Python developers can use the official openai library by adapting the base URL. This allows you to leverage the existing ecosystem of tools and SDKs. Configure the key and base_url to point to our servers. The uncensored model will process your input maintaining context up to 100,000 tokens.

This configuration is ideal for automation scripts or backend applications that need fast, uncensored responses. Response speed is usually high due to the dedicated infrastructure on our own GPU servers.

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)

Node.js Integration

In the JavaScript/Node ecosystem, integration is equally straightforward. Use the OpenAI SDK and override the base URL. This allows web applications or Node servers to consume unrestricted AI without changing your existing code logic. Error handling and promises work exactly as you expect with other OpenAI clients.

It is important to remember that the model is not GPT or Claude, but an open-weight model fine-tuned specifically for this service. This ensures consistent, uncensored behavior. Configure environment variables to keep your key secure in production.

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);

SSE Streaming

To improve the user experience, enable streaming by setting stream: true in your request. You will receive text chunks as they are generated, reducing perceived latency. This is crucial for real-time chat applications where users expect to see the response letter by letter.

Streaming maintains the same non-filtering properties as complete responses. You can process these chunks on the client or server side to render the response progressively. It is the best way to showcase the power of an uncensored AI chat in interactive applications.

Copiarstream = 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)

Limits and Error Handling

Your key has a rate limit of 300 requests per minute. If you exceed this threshold, you will receive a 429 error. There is also an 8 MB request body limit. If your key is invalid, you will get a 401; if you have no credit, a 402. The maximum context is 100k tokens combined (prompt + response).

The only strict content restriction is the prohibition of sexual content with minors, which always applies. For other topics, the model is very permissive. Check the standard OpenAI error codes to debug your integration quickly.