Quickstart Guide

Prerequisites: SDK and Key

Retrieve your API key from the dashboard and install your preferred language SDK. The service uses standard authentication headers, so you only need to pass the key securely. No phone number is required for signup, and the key appears immediately after creation. You can use Google or email credentials to access the panel.

Ensure your development environment supports the specific SDK version you choose. We recommend the latest stable release for best compatibility. The system accepts standard OpenAI-compatible clients, which simplifies the setup process significantly.

• Sign up via Google or email on the key page.
• Copy the generated API key immediately.
• Install the SDK for your preferred language.

Base URL Configuration

Point your client to the dedicated uncensored base URL and set the model identifier. The endpoint is HTTPS://api.llmwithoutrestrictions.com/v1. You must set the model ID to "uncensored" for every request. This ensures you are using the specific open-weight model tuned for unrestricted output.

Authentication relies on the Bearer token header. Pass your key exactly as provided. Do not modify the base URL structure. The API supports standard parameters like temperature and top_p. You can adjust these values to control creativity and determinism.

Sending Your First Request

Execute a simple chat completion to verify connectivity and response quality. Use the curl command below to send a direct request. This confirms the API key works and returns text without standard guardrail refusals.

Copycurl https://api.llmwithoutrestrictions.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the top five libraries for Rust async programming"}]
  }'

The response includes the generated text in the choices array. Check the usage statistics to monitor token consumption. This method is ideal for quick validation before integrating into larger applications.

Python SDK Integration

Initialize the client with your base URL and API key in Python. Use the OpenAI SDK or any compatible library. Set the model to "uncensored" explicitly. This approach handles retries and JSON parsing automatically.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.llmwithoutrestrictions.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 snippet demonstrates a straightforward message exchange. You can pass multiple messages for context. The system maintains state across the conversation window. This makes it easy to build conversational agents without complex routing logic.

Node SDK Integration

Configure the Node.js client with the correct base URL. Pass the API key in the headers. Specify the model ID as "uncensored". This ensures consistent behavior across your JavaScript applications.

Copyimport OpenAI from "openai";

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

Handle the response data to extract the generated content. The SDK manages the HTTP connection efficiently. You can integrate this into Express routes or serverless functions. The structure mirrors standard OpenAI responses for easy migration.

Streaming Responses and Limits

Enable streaming to receive tokens in real-time via Server-Sent Events. This reduces perceived latency for long outputs. The final chunk contains the total token usage statistics. Set the model parameter to "uncensored" to maintain consistency.

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)

You are limited to 300 requests per minute per key. The context window supports 100,000 tokens combined. Max output is 16,000 tokens per request. Errors like 401 or 402 are free. Rate limits apply strictly to prevent abuse. Keep request bodies under 8 MB.