What is the uncensored LLM chat API?

It is a hosted, OpenAI-compatible API serving one uncensored large language model. It supports text generation without content refusals for lawful adult use.

How do I pay for the uncensored AI API?

You pay with prepaid credit topped up via crypto (USDT on TRC20 or USDC on Base). There are no hidden subscription fees, and credit never expires.

What is the context window?

The context window is 100,000 tokens for prompt and completion combined. Max output per request is 16,000 tokens.

API Documentation - uncensored llm chat

Authentication

Use your API key in the Authorization header. We support Google or email login to generate the key instantly.

Include the header Authorization: Bearer YOUR_API_KEY in every request. The base URL for the uncensored LLM chat API is https://api.uncensoredllmchat.com/v1.

First Request

Send a POST request to /v1/chat/completions with the model ID uncensored. The model answers without content refusals for lawful adult content.

Set the system prompt to define behavior. The uncensored AI model supports a 100,000 token context window.

curl https://api.uncensoredllmchat.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "What is the capital of France?"}]
  }'

Python SDK Integration

Install the OpenAI Python package and configure the base URL. This ensures compatibility with the uncensored LLM chat endpoint.

Pass your API key and set the model to uncensored. The SDK handles tokenization and response parsing automatically.

from openai import OpenAI

client = OpenAI(base_url="https://api.uncensoredllmchat.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 SDK Setup

Initialize the OpenAI client with your custom base URL. This allows Node.js apps to use the uncensored AI API seamlessly.

Call chat.completions.create with the uncensored model ID. The uncensored LLM online experience is consistent with standard OpenAI behavior.

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.uncensoredllmchat.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 Responses

Enable streaming by setting stream: true. The API returns tokens via Server-Sent Events (SSE).

Parse the stream to display tokens in real time. The final chunk contains total token usage for billing.

stream = 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)

Limits and Errors

Expect a 401 error if the key is invalid. A 402 error means you need to top up with crypto (USDT/USDC).

A 429 error indicates you hit the 300 requests per minute limit. The context window is 100,000 tokens total.

API Documentation