Quickstart: Integrate the Uncensored LLM API

Prerequisites: SDKs and Environment Variables

Start by installing your preferred language SDK and storing your credentials securely. Our service uses standard authentication, so you only need an API key from the dashboard. Keep your key in an environment variable to avoid hardcoding it in your source files.

• Install the official SDK for your language.
• Create an account and generate your API key.
• Set IA_API_KEY in your environment.

This setup ensures your requests are authenticated immediately without extra configuration steps.

Step 1: Initialize the Client with Base URL

Point your client to our base URL to route requests correctly. You must override the default base URL to reach our uncensored model endpoint. This ensures all subsequent calls use the correct infrastructure.

Configure the base URL to https://api.iasansrestriction.com/v1 in your client settings. This single change directs traffic to our servers for text generation.

Step 2: Send Your First Chat Completion

Make your first request to test the connection and receive text output. Use the model ID uncensored to access the unrestricted large language model. This model does not refuse lawful adult or controversial topics by default.

Send a POST request to /v1/chat/completions with your system and user messages. The response will contain the generated text without standard content filters.

Step 3: Handle Streaming Responses (SSE)

Enable streaming for real-time token delivery to improve user experience. Set the stream parameter to true in your request body. The server will return a Server-Sent Events (SSE) stream of chunks.

Process each chunk as it arrives to display text incrementally. This approach reduces perceived latency for long-form content generation.

Step 4: Use Function Calling and JSON Mode

Structure your data output using built-in formatting features. You can enforce JSON responses by setting response_format to {"type": "json_object"}. This ensures predictable parsing for downstream applications.

Define tools in your request to enable function calling capabilities. The model will return structured arguments that your code can execute directly.

Step 5: Manage Tokens and Limits

Monitor your usage to avoid service interruptions and manage costs. You are charged per token, with errors and refusals being free. Credit never expires, so you can top up when needed.

Respect the limits: 300 requests per minute and a 100,000 token context window. A 429 error indicates you have exceeded the rate limit. A 401 error means your key is invalid, while a 402 error signals insufficient credit.

cURL

Copycurl https://api.iasansrestriction.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Generate a list of ten valid JSON objects"}]
  }'

Python

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.iasansrestriction.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

Copyimport OpenAI from "openai";

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

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)