Abliterate API Quickstart Guide

Install the Standard OpenAI SDK

Start by installing the official library for your preferred language. This ensures compatibility with our base URL and authentication methods.

Configure Your Base URL and Key

Point your client to HTTPS://api.abliterate.cc/v1 and use your unique API key. You get one active key per account, which you receive immediately after signing up with Google or email.

• Base URL: HTTPS://api.abliterate.cc/v1
• Auth: Bearer token via Authorization header

This setup works with any standard OpenAI-compatible client.

Send Your First Completion Request

Send a POST request to /v1/chat/completions with the model ID uncensored. The model processes text in and text out without generic guardrails.

Copycurl https://api.abliterate.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the top five Python libraries for web scraping in 2024"}]
  }'

Check the response for the generated text. You can adjust parameters like temperature for creativity or top_p for diversity.

Enable Streaming for Real-Time Output

Set stream: true to receive tokens via Server-Sent Events (SSE). This provides a smoother experience for chat interfaces.

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)

The final chunk contains the total token usage. Streaming works for all standard parameters.

Use Tool Calling and JSON Mode

Enable structured outputs with response_format: {"type": "json_object"} for consistent parsing. You can also use tools and tool_choice for function calling.

Copyfrom openai import OpenAI

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

These features work alongside standard parameters like stop sequences and seed for reproducibility.

Handle Errors and Token Limits

Monitor HTTP status codes for common issues. A 401 means your key is invalid or missing. A 402 indicates insufficient prepaid credit. A 429 signals you hit the 300 requests per minute limit.

The context window is 100,000 tokens total. Max output is 16,000 tokens per request. Errors and refusals do not consume your credit.

Copyimport OpenAI from "openai";

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