Quickstart Guide

Model Abliterated

Set base URL and key

Start by generating an API key on the dashboard. Use "Continue with Google" or a standard email login to create your account instantly. No phone number verification is required. Once the key appears, copy it to your environment variables. Our API base URL is HTTPS://api.modelabliterated.com/v1. Update your SDK configuration to point to this URL instead of the default OpenAI endpoint. This ensures all requests route to our uncensored infrastructure.

Send your first request

Make a POST request to /v1/chat/completions. Set the model ID to "uncensored". Pass your system prompt to guide the behavior. The abliterated model responds directly without extra fluff. Here is how you can send a simple text completion using curl.

Copycurl https://api.modelabliterated.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "what is the capital of france"}]
  }'

Use the Python SDK

Install the official openai package via pip. Initialize the client with your API key and the custom base URL. The Python SDK handles serialization automatically. You can send a message and get the full response text. This method is ideal for backend scripts or local inference testing.

Copyfrom openai import OpenAI

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

Integrate with Node.js

Require the openai npm package in your project. Configure the base URL and apiKey properties on the client instance. Call chat.completions.create with the model and messages. The response object contains the generated text in choices[0].message.content. This approach works well for server-side rendering or API endpoints.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.modelabliterated.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);

Handle streaming responses

Enable streaming by setting stream to true in your request parameters. The API returns chunks of tokens as they are generated. This reduces perceived latency for long outputs. You can process each chunk in real-time. Use the final chunk to check total token usage and billing data.

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)

Manage limits and errors

You have a 100,000 token context window for prompt and completion combined. The rate limit is 300 requests per minute per key. If you exceed this, you receive a 429 error. A 401 error means your key is invalid. A 402 error indicates insufficient prepaid credit. Ensure you top up with USDT or USDC to continue. Errors do not consume tokens. The max output per request is 16,000 tokens unless you specify a lower max_tokens value.