Abliterated Models API Documentation

Base URL and Authentication

Use the base URL https://api.abliteratedmodelhub.com/v1 with any standard OpenAI-compatible client. Pass your API key in the Authorization header as a Bearer token. Every account starts with a unique key shown immediately after signup, which you can regenerate at any time to revoke the old one. No phone number or credit card is required to begin.

Authentication failures return a 401 status if the key is invalid or missing. Billing errors return a 402 status if your prepaid credit is exhausted. You can top up from $10 using crypto (USDT or USDC), and bonus credit is applied at higher tiers.

First Request

Send a basic chat request to the /v1/chat/completions endpoint. The model ID is uncensored. This is a text-in, text-out API designed for abliterated models that do not refuse lawful adult or controversial topics.

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

The request body includes the standard messages array. The model responds with generated text. This is not a multi-model marketplace; you are interacting with one specific open-weight model tuned for minimal refusal.

Python SDK

Use the official OpenAI Python SDK or any compatible library. Set the base URL to our endpoint and provide your API key. The client treats our service as a standard OpenAI-compatible provider.

Copyfrom openai import OpenAI

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

This approach works for simple text generation or complex prompt engineering. The model handles the abliterated weights on our GPU servers, so you do not need to manage local inference or VRAM constraints.

Node SDK

Initialize the OpenAI client in Node.js with the custom base URL. Pass your API key as the authorization token. The model parameter should be set to uncensored.

Copyimport OpenAI from "openai";

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

Node.js developers can use this setup for server-side generation or integration into larger applications. The API supports standard JSON payloads and returns structured completions.

Streaming Responses (SSE)

Enable streaming by setting stream: true in your request. The API returns Server-Sent Events (SSE) for real-time token delivery. This is useful for UIs that display text as it is generated.

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 does not change the model behavior or context window. It only affects how the response is delivered. Each chunk contains a partial completion until the generation is complete.

Rate Limits, Errors, and Context

Each API key is limited to 300 requests per minute. The maximum request body size is 8 MB. The context window is 100,000 tokens for both input and output combined. If you exceed the limit, the API returns a 429 status code. Requests are blocked if they contain sexual content involving minors, which is a hard content limit. Prompts are not used for training your data.