Uncensored ia API Quickstart

Installation and setup

Install the official SDK for your preferred language. Our API works with any standard OpenAI-compatible client, so you can use the libraries you already trust. The setup process requires no special configuration beyond adding the dependency to your project environment.

You will need an API key to authenticate your requests. Generate one immediately after signing up via Google or email. The key appears on your screen once, so copy it to your clipboard or secure storage right away. Keep it private to avoid unauthorized usage from your prepaid balance.

Configuration: base_url and key

Point your client to our base URL and set the API key header. Use the specific endpoint provided in your dashboard. This ensures your requests go directly to the uncensored model without any routing ambiguity. The base URL is HTTPS://api.iasemsensura.com/v1.

Set the Authorization header to Bearer YOUR_API_KEY. This header authenticates every request you send. Without the correct key, the API will reject your input with a 401 error. Always verify your key matches the one shown during signup.

Sending your first request

Send a simple chat completion request to test connectivity. Use the model ID uncensored to ensure you get the correct output. This model is tuned for unrestricted text generation. It handles roleplay and adult themes without standard refusals.

Here is a basic cURL example to get you started. Replace the placeholder with your actual API key. This command sends a short prompt and expects a direct response.

Copycurl https://api.iasemsensura.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Generate 200 words of dark fantasy lore"}]
  }'

Handling streaming responses

Enable streaming for real-time token generation. This is crucial for applications that display text as it is generated. The API returns events via Server-Sent Events (SSE). You receive chunks of text as they become available.

Use the Python SDK to handle streaming efficiently. The library manages the connection and yields tokens as they arrive. This approach reduces perceived latency for end users. It also allows for immediate display of partial results.

Copyfrom openai import OpenAI

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

Function calling and JSON mode

Use function calling for structured data extraction or tool use. Define your tools in the request body. The model will return a JSON object with the required arguments. This feature works alongside standard text generation.

Enable JSON mode to force the output into a specific format. Set response_format to {"type": "json_object"}. This ensures the response is valid JSON. Use the Node SDK for easy integration with JavaScript environments.

Copyimport OpenAI from "openai";

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

Understanding token usage and limits

Monitor your token usage and request limits closely. The context window supports up to 100,000 tokens per request. This includes both the input prompt and the generated output. Max output is 16,000 tokens unless you specify otherwise.

You are limited to 300 requests per minute per key. Concurrency is capped at 8 simultaneous requests. If you exceed these limits, you will receive a 429 error. Streaming responses also count towards these limits. Use the usage field in the final chunk to track consumption.

Streaming

Copystream = 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)