Quick Integration with the Uncensored API

Initial Setup and Authentication

To start using the uncensored api, you need a valid API key. Go to the Get API key page with your email and password. The key is displayed immediately after registration, without needing a card for the trial credit.

All requests must include the Authorization: Bearer sk-... header. If the key is invalid, the server returns error 401. Remember: each account has only one active key, but you can regenerate it at any time, invalidating the previous one.

First Request

The main endpoint is POST /v1/chat/completions. The available model is identified as "uncensored". It is an open-weight model, tuned to not refuse lawful adult, fictional, or research topics.

Below is a basic example using curl to send a simple message.

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

Note that the response will contain the full text generation. There are no embeddings or image generation in this specific endpoint.

Python Integration

If you prefer Python development, the official openai library works perfectly, just point to the correct base_url. This ensures familiarity with the standard request structure.

Set the base URL to https://api.apisemrestricoes.com/v1 and enter your key in the environment variable or directly in the client. The code below demonstrates creating a simple conversation.

Copiarfrom openai import OpenAI

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

Remember that the model is not GPT or Claude; it is a proprietary open-source architecture optimized for content freedom.

Node.js Integration

For JavaScript or TypeScript environments, use the Node.js openai SDK. The configuration is similar to Python: adjust the baseURL and authenticate.

The code below shows how to create a client instance and send a chat completion request. The response is processed synchronously by default, but for continuous data flows, see the streaming section.

Copiarimport OpenAI from "openai";

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

This method is ideal for backend applications that process text without needing real-time browser updates.

Streaming via SSE

Server-Sent Events (SSE) support allows receiving responses token by token, improving latency perception for the end user. Enable streaming by setting stream: true in your request.

The example below illustrates how to consume the stream in parts, allowing text to be displayed gradually.

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)

This is particularly useful for chat interfaces where users prefer to see the model "typing" in real time, without waiting for the full response to complete.

Limits, Errors, and Context Window

Your account is subject to specific limits to ensure service stability. The limit is 300 requests per minute per key. The request body cannot exceed 8 MB.

Common errors include: 401 (invalid key), 402 (insufficient credit), and 429 (rate limit exceeded). The total context window (prompt + completion) is 100,000 tokens. If you need more contextual memory capacity, adjust the size of the messages sent.