What is abliteration and why does it matter for uncensored use?

Abliteration removes specific model behaviors that cause refusals. This process allows the model to answer controversial or adult topics without hedging. It results in a more direct and honest response style for unrestricted applications.

How do I top up my credit?

Top up using crypto only. Accept USDT on TRC20 or USDC on Base. Minimum amount is $20. Maximum is $500. Bonus credit applies for larger amounts. Credit never expires.

Which payment methods do you accept?

Crypto only: USDT on TRC20 or USDC on Base, any whole amount from $20 to $500. Bonus credit applies from $50.

Abliteration API Documentation

Authentication and Base URL

Your API key authenticates every request. Use https://api.whatisabliteration.com/v1 as your base URL. Pass your key in the Authorization header as a Bearer token. This setup works with any OpenAI-compatible client.

curl https://api.whatisabliteration.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Show me last 5 requests"}]
  }'

Keep your key secure. One key per account. Replace old keys if compromised.

Chat Completions Endpoint

Send text to POST /v1/chat/completions. The model id is uncensored. This endpoint handles all text generation. It does not support images, audio, or video. You pay only for tokens used. Errors are free. Refusals are free.

from openai import OpenAI

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

Configure your system prompt to define the persona. The model answers directly without hedging. Context window is 100,000 tokens total.

Streaming and SSE Support

Enable streaming by setting stream: true. The API returns Server-Sent Events (SSE). Each chunk contains partial text. The final chunk includes token usage data. This reduces perceived latency for long responses.

stream = 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)

Handle partial tokens carefully. Concatenate them to form the complete response. This is ideal for real-time chat interfaces.

Function Calling and Tools

Define tools in your request. The model can call functions when appropriate. Use tool_choice to control behavior. Set temperature for creativity. Pass parameters like top_p and stop. This allows complex agent workflows.

import OpenAI from "openai";

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

Validate tool outputs in your code. The model suggests actions. You execute them. This structure supports advanced automation tasks.

JSON Mode Response Format

Set response_format to {"type": "json_object"}. The model outputs valid JSON only. This ensures structured data for parsing. Use this for APIs that expect strict formats. It improves reliability for downstream systems.

Use this mode when integrating with other services. Parse the output directly. Avoid regex hacks for structure.

Parameters and Constraints

Max output is 16,000 tokens. Default max is 2,048 tokens. Context window is 100,000 tokens. Rate limit is 300 requests per minute. Concurrent requests are 8 per key. Request body max is 8 MB. Handle 401 for invalid keys. Handle 402 for no credit. Handle 429 for rate limits.

API Documentation