Uncensored LLM API Quickstart | Uncensored LLM Hub

Base URL & Authentication

Use the base URL https://api.uncensoredllmhub.com/v1 for all requests. Authentication requires an API key passed in the Authorization header as a Bearer token. You receive this key immediately upon signup via the Get API key page. The key is tied to a single account; you can regenerate it at any time, which invalidates the previous key. No phone number or credit card is required to start.

POST /v1/chat/completions

Send your prompt to the chat endpoint. The model id is always uncensored. The API accepts standard chat messages and returns text. It does not support images, audio, or embeddings. Ensure your request body stays under 8 MB. The following example demonstrates a basic text request using cURL:

Copycurl https://api.uncensoredllmhub.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."}]
  }'

This returns a completion for your prompt. You can parse the response to extract the generated text for your application logic.

Python SDK Integration

Use the official openai Python package for easier integration. Configure the client with your base URL and API key. This approach simplifies JSON handling and type inference. The following example shows how to initialize the client and send a message:

Copyfrom openai import OpenAI

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

Replace YOUR_API_KEY with your actual key. The response object provides direct access to the content, making it easy to integrate into Python workflows.

Node SDK Integration

For JavaScript environments, use the OpenAI Node.js SDK. Set the base URL and API key in the configuration object. This allows you to use standard promise-based syntax. The following example demonstrates a simple chat completion:

Copyimport OpenAI from "openai";

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

Ensure you handle the asynchronous response appropriately. This method works well for server-side applications or Node.js environments where you need to process the output immediately.

Streaming Responses (SSE)

Enable streaming by setting stream: true in your request. The API returns Server-Sent Events (SSE) instead of a single JSON object. This allows you to display tokens as they are generated, improving perceived latency. The following example shows how to handle the stream in Python:

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)

Parse each chunk to extract the delta content. This is useful for chat interfaces where users expect real-time typing indicators. The stream ends when the final chunk is received.

Rate Limits, Errors & Context

You are limited to 300 requests per minute per key. If you exceed this, you receive a 429 error. Other common errors include 401 (invalid key) and 402 (insufficient credit). The context window is 100,000 tokens for prompt plus completion combined. If your input is too large, the model may truncate or reject the request. Always monitor your usage via the dashboard to avoid service interruptions.