Integrate the Uncensored AI LLM API

Configure Your Base URL

Start by pointing your client to our dedicated endpoint. Use https://api.uncensoredaillm.com/v1 as your base URL. This ensures all requests hit our uncensored infrastructure directly. You do not need to change model names unless you specify uncensored explicitly.

Authentication relies on a single API key generated from your dashboard. Pass it in the Authorization header as a Bearer token. This key grants access to your prepaid credit. Errors like 401 indicate an invalid key, while 402 means you need to top up via crypto.

Send Your First Completion

Make a POST request to /v1/chat/completions with your messages array. The model ID must be set to uncensored. This model does not refuse lawful adult, fictional, or controversial topics. It is not GPT, Claude, or any other vendor's model.

Set the max_tokens parameter to control output length. The default is 2,048 tokens. You can increase this up to 16,000 tokens per request. The total context window is 100,000 tokens. This includes both prompt and completion.

Quickstart with Python

Use the official OpenAI Python SDK to integrate quickly. Install the package and initialize the client with our base URL. Pass your API key as the api_key argument.

Node SDK Integration

Initialize the OpenAI client in Node.js. Set apiKey to your token and baseURL to our endpoint. Call chat.completions.create with the model uncensored. This works with any OpenAI-compatible client library.

Enable Streaming Responses

Set stream: true in your request body. The API returns data via Server-Sent Events (SSE). Each chunk contains partial content. Token usage details appear in the final chunk. This allows real-time display of generated text. It reduces perceived latency for long responses.

Limits, Errors, and Context

You are limited to 300 requests per minute per key. Concurrent requests are capped at 8. Request bodies must be under 8 MB. A 429 error indicates you have hit the rate limit. Increase your interval or reduce concurrency. The context window supports 100,000 tokens total. Refusals for minor sexual content are hard-coded. All other lawful content is allowed. Credit never expires. Use crypto to top up when needed.

cURL

Copycurl https://api.uncensoredaillm.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Run npm install"}]
  }'

Python

Copyfrom openai import OpenAI

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