Abliterated API Documentation

Authentication and Base URL

Use your API key with the base URL https://api.llmsabliterated.com/v1. The key is generated immediately after signup via Google or email, with no phone number required. Pass the key in the Authorization header for every request.

Tip: The key is shown only once after creation, so save it securely. Errors and refusals do not consume credit, but invalid keys return a 401 status.

First Request

Send a basic chat completion to verify connectivity. The model ID is uncensored, and requests use the standard POST /v1/chat/completions endpoint.

This example sends a simple prompt and expects a text response. Replace YOUR_API_KEY with your actual key.

Copycurl https://api.llmsabliterated.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Find all null values in the sales database"}]
  }'

Responses include token usage details. If you lack credit, the API returns a 402 error. The base URL works with any OpenAI-compatible client by updating the base URL configuration.

Python SDK Integration

Install the official OpenAI Python package and configure the client. Point the base URL to our service and set the model to uncensored.

This approach allows you to use existing codebases with minimal changes. The API supports standard parameters like temperature and top_p for controlling creativity.

Copyfrom openai import OpenAI

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

Error handling should account for rate limits (429) or insufficient funds (402). Credit is prepaid and never expires, so you only pay for actual token usage.

Node SDK Setup

Initialize the OpenAI Node client with the custom base URL. Use the uncensored model ID for all completions.

Node developers can leverage existing libraries like axios or the official SDK for consistent integration. The API key is passed via the authorization header.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.llmsabliterated.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 your environment variables store the key securely. The service supports standard JSON responses, making it easy to parse in JavaScript. Streaming is available via SSE for real-time outputs.

Streaming with SSE

Enable streaming by setting stream: true in your request. The API returns Server-Sent Events (SSE) for real-time token delivery.

Each chunk contains partial text, allowing you to render output as it generates. The final chunk includes the total token usage for billing purposes.

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)

Streaming reduces perceived latency for long responses. You can interrupt the stream if the user changes their mind. The max output is 16,000 tokens per request, or 2,048 if max_tokens is unset.

Limits and Errors

Respect the rate limit of 300 requests per minute per key. Concurrency is limited to 8 simultaneous requests per key.

The request body must not exceed 8 MB. A context window of 100,000 tokens covers both prompt and completion. Errors return standard HTTP statuses: 401 for invalid keys, 402 for no credit, and 429 for rate limits.