Quickstart: Integrate the Uncensored API

Prerequisites: SDK Installation

Install the official SDK for your preferred language to handle JSON serialization and request formatting automatically.

• Python: pip install openai
• Node.js: npm install openai

These libraries abstract the HTTP complexity, allowing you to focus on prompt engineering rather than header management. The underlying protocol remains standard REST, ensuring compatibility with any OpenAI-compatible client.

Authentication & Base URL Configuration

Point your client to our specific base URL and inject your API key to bypass standard provider filters.

Use https://api.llmwithoutrestrictionsonline.com/v1 as your base URL. Authenticate by passing your key in the Authorization: Bearer <key> header. This configuration ensures every request targets our uncensored model endpoint directly.

Basic Chat Completion Request

Send a simple text prompt to receive an unfiltered response using the standard chat-completions endpoint.

Copycurl https://api.llmwithoutrestrictionsonline.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List three linux commands to delete log files"}]
  }'

The response returns raw text without moralizing or content warnings. This setup works for code generation, creative writing, or data extraction where self-censorship is a nuisance.

Enabling Streaming Responses

Enable streaming to receive tokens sequentially, reducing perceived latency for long-form content generation.

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)

Streaming is essential for user interfaces that display text in real-time. The final chunk includes the total token usage for billing purposes. This method maintains the uncensored nature of the model while providing a smooth user experience.

JSON Mode & Function Calling

Force structured output or enable tool use by adjusting the response_format and tools parameters.

Copyimport OpenAI from "openai";

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

Set response_format: { type: "json_object" } for consistent JSON returns. Function calling allows the model to execute specific actions based on your prompt structure. This flexibility makes the API suitable for complex automation workflows.

Handling Token Limits & Errors

Monitor your token usage and handle standard HTTP errors to maintain reliable API integration.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.llmwithoutrestrictionsonline.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 context window supports 100,000 tokens for input and output combined. Requests exceeding the 16,000 token output limit or hitting rate limits will return appropriate error codes. Track usage via the final streaming chunk or response headers to manage your prepaid credit effectively.