Quick Guide to Using the Uncensored AI API

Configure Base URL and Authentication

To get started, you need to configure the base URL so that the OpenAI-compatible SDK points to our server. Use https://api.apitanpasensor.com/v1 as the main endpoint. Authentication is done via the Authorization: Bearer YOUR_API_KEY header. The API key you receive upon registration is unique and valid for only one account. If you regenerate the key, the old key is immediately revoked and can no longer be used, even though the old key does not expire automatically over time.

A First Request Example

Send a POST request to /v1/chat/completions with the uncensored model. This is an open-weight model that does not filter legitimate or controversial adult topics, unlike standard enterprise models.

Salincurl https://api.apitanpasensor.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."}]
  }'

Make sure to include the model parameter with the value uncensored. The response will be a JSON containing the text generated by the model.

Python SDK Integration

Use the openai library in Python to interact with the API. Set base_url and api_key according to the configuration above. The uncensored model supports a context length of up to 100,000 tokens, allowing you to send very long prompts without losing important information.

Salinfrom openai import OpenAI

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

The code example above shows how to send system and user messages simply.

Node.js SDK Integration

For Node.js users, the OpenAI SDK can also be configured easily. Set baseURL to our endpoint URL and use your API key. This approach allows you to integrate uncensored AI into your web application or server-side quickly.

Salinimport OpenAI from "openai";

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

Remember that this model handles text only and does not support image, audio, or video generation.

Enable Streaming (SSE)

For a more responsive user experience, enable streaming by adding stream: true to the request parameters. The API will return the response using Server-Sent Events (SSE). This is very useful for real-time chat applications where users see results token by token.

Salinstream = 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)

Streaming does not change the price or token limit, only the way the response is delivered.

Limits, Errors, and Context Management

This API has a limit of 300 requests per minute per key and a maximum request body size of 8 MB. If the key is invalid, you will receive a 401 error. If your credit balance is exhausted, a 402 error will appear. Error 429 indicates you have exceeded the rate limit. The context window is 100,000 tokens for combined prompt and completion. Make sure to manage tokens wisely so as not to exceed this limit.