API Documentation

Base URL and Authentication

Direct your requests to the documented base URL using a single API key.

The base URL is HTTPS://api.aitheuncensored.com/v1 and requires the standard Authorization header.

One active key per account replaces the previous one immediately upon generation.

No phone number is needed for signup, and the key appears instantly after you create an account via Google or email.

Errors and refusals consume zero tokens, so you only pay for actual output.

Keep your key secure because it grants full access to your prepaid balance.

First Request

Send a standard chat completion payload to receive immediate text output.

The model identifier is strictly "uncensored" and runs on our own optimized servers.

This single open-weight model answers without content refusals for lawful adult use.

Input goes in, text comes out, and you control the context window up to 100,000 tokens.

Errors do not charge your account, ensuring predictable billing for every attempt.

Use the official OpenAI SDKs by simply updating the base_url configuration.

Python SDK Integration

Initialize the client with your base URL and API key to start generating text.

The Python SDK handles the HTTP transport automatically, reducing boilerplate code.

You can stream responses or retrieve full text based on your application needs.

Set the model to "uncensored" to ensure consistent, unfettered output behavior.

Temperature and top_p parameters allow you to adjust creativity levels precisely.

Errors return standard HTTP codes, making debugging straightforward for integration engineers.

Node SDK Usage

Configure the Node.js client to point at our API endpoint for reliable data flow.

The package supports modern async/await patterns for clean, readable request handling.

Pass the "uncensored" model ID to maintain compatibility with existing OpenAI workflows.

JSON mode is available via the response_format parameter for structured data extraction.

Streaming via Server-Sent Events provides real-time token delivery for dynamic interfaces.

The API key authenticates every request, ensuring your prepaid credit is used correctly.

Streaming and JSON Mode

Enable streaming by setting stream to true for real-time token delivery.

The final chunk includes the total token usage for accurate billing tracking.

Request JSON mode by setting response_format to json_object for structured data.

This feature ensures predictable output formats for automated pipelines and scripts.

Function calling is supported via the tools parameter for enhanced capability.

Both streaming and JSON mode work independently or together depending on your needs.

Rate Limits and Error Codes

Monitor your usage against the 300 requests per minute and 8 concurrent request limits.

A 401 error indicates an invalid or missing API key in the Authorization header.

A 402 error means your prepaid credit is exhausted and requires a crypto top-up.

A 429 error signals that you have exceeded the rate limit for your key.

The context window allows 100,000 tokens for both prompt and completion combined.

Max output is 16,000 tokens per request, or 2,048 if max_tokens is unset.

cURL

Copycurl https://api.aitheuncensored.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the top 5 latency metrics for the current endpoint"}]
  }'

Python

Copyfrom openai import OpenAI

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