What crypto options are available for top-ups?

You can top up with USDT (TRC20) or USDC (Base). Amounts range from $10 to $500. You receive a +5% bonus on $50 and +10% on $100. No cards or PayPal are accepted.

Does the abliterated model have content restrictions?

It is uncensored for lawful adult, fictional, and controversial topics. However, a hard limit blocks sexual content involving minors. This restriction always applies regardless of your settings.

How does billing work with errors?

You pay only for actual token usage. Errors and refusals do not consume credit. Your prepaid credit never expires, so you can use it whenever needed without monthly fees.

API Documentation

Authentication and Base URL

Start by generating an API key on the Get API key page. You can sign in with Google or use email and password. The key appears immediately; no phone number is required. Use the base URL https://api.abliterated.top/v1 with any OpenAI-compatible client. Your API key authenticates all requests.

curl https://api.abliterated.top/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 endpoint is POST /v1/chat/completions. Pass your key in the Authorization header. The model ID is uncensored. This is an open-weight model, not GPT or Llama, tuned for no refusals on lawful adult topics.

First Request with Python

Use the official Python SDK to send your first prompt. Configure the base URL and API key. The model ID remains uncensored. This setup works for both simple text generation and complex coding tasks. The abliterated llm handles context windows up to 64,000 tokens total.

from openai import OpenAI

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

Set the model parameter to uncensored. The API returns text responses. You can adjust parameters like temperature and top_p for varied outputs. Errors do not consume credit.

Node.js SDK Integration

For Node.js developers, the official SDK works with minor configuration changes. Set the base URL to our API endpoint. The abliterated uncensored ai model responds to standard chat completion requests. This allows easy integration into existing workflows without rewriting logic.

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.abliterated.top/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 you pass the correct API key. The response includes the generated text. You can parse the output for further processing. This uncensored coding llm supports various programming languages without content filters blocking standard syntax or concepts.

Streaming Responses

Enable streaming by setting stream: true. The API returns data in chunks via Server-Sent Events (SSE). Token usage details are included in the final chunk. This provides a responsive user experience for long outputs.

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 each chunk as it arrives. The abliterated model maintains context throughout the stream. You can accumulate the text or process it in real-time. Max output per request is 16,000 tokens, or 2,048 if max_tokens is unset.

JSON Mode and Parameters

For structured outputs, use response_format: {"type": "json_object"}. This ensures the abliterated model returns valid JSON. Useful for parsing data or generating code structures. You can also set temperature, top_p, stop, seed, and penalty parameters.

Function calling and tool choices are supported. The abliterated models open source nature means no restrictions on how you use the output. Ensure your JSON is well-formed. Errors in formatting do not incur extra charges.

Rate Limits and Errors

Each key allows 300 requests per minute and 8 concurrent requests. The request body max is 8 MB. Use one active key per account; a new key replaces the old. Errors like 401 (invalid key) or 402 (no credit) are free. Rate limits return 429.

The context window is 64,000 tokens total. Credit is prepaid via crypto. No subscription fees. Credit never expires. Refunds are not issued, but mistakes are fixed via Support.

Quickstart Guide