API Documentation

Authentication and Base URL

Start by generating your key via the dashboard. Use https://api.abliteratedaimodel.com/v1 as your base URL. Pass the key in the Authorization header. No subscriptions or monthly fees apply. Your prepaid credit covers usage until depleted.

First Request

Send a simple text completion to verify connectivity. The uncensored model responds instantly to standard prompts. Replace YOUR_API_KEY with your generated credential. The response includes the generated text and token usage.

Copycurl https://api.abliteratedaimodel.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Generate a hello world function in python"}]
  }'

Python SDK Integration

Use the official OpenAI Python library for easy integration. Set the base URL to our endpoint. Initialize the client with your API key. Send messages and receive raw text output. This approach works for most standard LLM applications.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.abliteratedaimodel.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

Import the OpenAI package in your Node.js project. Configure the API key and base URL. Make a chat completion request with your desired prompt. Handle the response data asynchronously. This method suits server-side JavaScript environments perfectly.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.abliteratedaimodel.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 for lower latency with long outputs. Set stream to true in your request. Receive chunks as they generate. Process each chunk to update your UI in real time. This reduces perceived wait times significantly.

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)

Limits and Errors

Context windows support 100,000 tokens total. Max output per request is 16,000 tokens. Rate limits allow 300 requests per minute. Handle errors like 401 for invalid keys or 402 for insufficient credit. Plan your token usage carefully to avoid interruptions during high-volume tasks.