Quickstart: Use the Uncensored LLM API

Prerequisites

Before making requests, ensure you have a valid API key. Sign up on our Get API key page using just an email and password. Your key is displayed immediately after signup. You start with $0.50 in trial credit, valid for 7 days, with no credit card required. For heavier usage, top up prepaid credits starting at $10. The API uses a single uncensored model, identified as uncensored, hosted on our own infrastructure. It is not a proxy for GPT, Claude, or other vendor models. You need only a basic understanding of HTTP requests or one of the standard OpenAI-compatible SDKs.

Authentication

Include your API key in the Authorization header of every request. Use the Bearer scheme followed by your key string. The base URL for all endpoints is https://api.anonymousllmapi.com/v1. This URL works with any client that supports the OpenAI API format. If your key is invalid or expired, the server returns a 401 error. If you have no credit, it returns a 402 error. Regenerate your key anytime from your dashboard to revoke the old one instantly. No phone number or billing details are needed for the initial trial.

Basic Chat Completion

Send a POST request to /v1/chat/completions to get a text response. The model uncensored processes your prompt and returns text without content filtering for lawful adult use. Below is a basic example using curl. Replace YOUR_API_KEY with your actual key. The request body includes the model ID and your message history. The API returns a JSON object with the generated text. This is a pure text API; do not expect images or audio in the response.

Python SDK Integration

Use the official OpenAI Python SDK to interact with our API. Configure the base_url to point to our endpoint and set the api_key. This allows you to use familiar methods like client.chat.completions.create. The model ID remains uncensored. This approach simplifies header management and JSON parsing. It is ideal for backend services or scripts where you need structured data handling. Ensure your SDK version is compatible with the OpenAI API specification. Our API supports standard parameters like temperature and max_tokens.

Streaming Responses

Enable streaming by setting stream: true in your request. The API returns a Server-Sent Events (SSE) stream of partial responses. This reduces perceived latency for users waiting for long outputs. Each chunk contains a portion of the generated text. Handle the stream in your client code to append tokens as they arrive. This is useful for chat interfaces where real-time typing effects are desired. The stream ends when the model completes the response or hits the context limit. Use the appropriate SDK method for streaming to handle events correctly.

Rate Limits and Constraints

Each API key is limited to 300 requests per minute. If you exceed this, the API returns a 429 error. The maximum request body size is 8 MB. The context window is 64,000 tokens, combining both input prompt and output completion. This limit applies to the total tokens processed in a single request. Function calling is supported within this window. Pay-as-you-go credits never expire. If you run out of credits, requests fail with a 402 error. Top up anytime to continue service. These limits ensure consistent performance for all users on our dedicated infrastructure.

cURL

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

Python

Copyfrom openai import OpenAI

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