Uncensored API

What Is Abliteration: The Uncensored API

Get an open-weight uncensored LLM via OpenAI-compatible API with a 100,000-token context window, paying only for real token usage.

100,000 token context window
Crypto-only top-ups
$0.50 trial credit

Try with trial credit View documentation

Test with a single call

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"}]
  }'

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)

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);

$0.15per 1M input tokens
$0.50Output tokens / 1M
100,000token context
$0.50trial credit
300requests per minute

Core features

OpenAI-Compatible Interface

Drop it into your existing stack using standard endpoints and SDKs without complex routing logic.

Massive Context Window

Process up to 100,000 tokens per request for deep context retention in long conversations.

Streaming Support

Receive real-time token updates via Server-Sent Events with usage data included in the final chunk.

Advanced Parameters

Fine-tune responses using temperature, top_p, stop sequences, and seed control for precise generation.

JSON Mode

Force structured output using the response_format parameter for reliable data extraction and tool integration.

Private by Design

No phone number required, no training on your prompts, and prepaid credit that never expires.

Setup guide

Create Account

Top Up Crypto

Add credit using USDT (TRC20) or USDC (Base) with bonus incentives.

Send Requests

Call the chat-completions endpoint and start generating uncensored text immediately.

Built with this API

Roleplay Applications

Deploy characters that stay in context without soft refusals breaking immersion.

Content Creation

Generate unrestricted narratives, scripts, or creative writing with minimal hedging.

Data Extraction

Parse large documents using JSON mode for consistent structured output.

Research Tools

Analyze controversial topics without corporate bias interfering with the results.

The 6-Point Checklist for Choosing an Uncensored Provider

Verify these six criteria to ensure your NSFW chatbot provider won’t silently filter your prompts.

Confirm no training on your data preserves privacy.
Check that the base URL is truly OpenAI-compatible for easy SDK swaps.
Ensure pricing is per-token with no hidden monthly subscriptions.
Validate that crypto-only payments avoid unnecessary identity tracking.
Confirm the model is uncensored for lawful adult content without soft refusals.
Verify strict rate limits and clear request body constraints.

Real Math: Token Arithmetic and Cost Examples

Costs scale strictly with token volume at $0.15 per million input tokens and $0.50 per million output tokens. A 5,000-input, 2,000-output request totals $0.00175. Streaming via SSE reveals usage in the final chunk. Prepaid credit never expires. Errors cost nothing. You only pay for what actually leaves the server.

What Is Abliteration: Unlocking Raw Model Potential

Abliteration removes the safety layers that cause soft refusals, letting the base model answer directly without hedging.

NSFW Chatbot

Eliminate generic refusals for adult content while keeping the model’s native logic intact.

Roleplay

Deep characters stay in context without suddenly breaking character to ask if you are sure.

Security Research

Get raw outputs for jailbreak testing without the model apologizing for its own answers.

Common Mistakes in Uncensored API Integration

Developers often assume uncensored means unlimited context, but our model caps output at 16,000 tokens per request. Many forget to set response_format: {"type": "json_object"}, causing parsing errors when building NSFW chatbots that expect structured data. Another error is ignoring the 8 MB body limit during bulk streaming. Always verify your client handles SSE streams correctly, as this ensures reliable token usage tracking without wasting prepaid credit on malformed responses.

Who It Is For (And Who It Isn't)

Developers building NSFW chatbots or roleplay engines need this uncensored LLM for direct, refusal-free responses.

Use cases: unrestricted content generation, creative writing, and adult-oriented applications.
Best for: those who want an open-weight model without corporate hedging.

It is not for users needing image generation, embeddings, or fine-tuning.

Not suitable: teams requiring multi-model routing or specific certifications like HIPAA.

This API delivers raw output for lawful adult use, ensuring your prompts shape the context without hidden filters.

From Signup to First Token: How It Works

Visit the Get API Key page and authenticate via Google or email with no phone number required.
Receive your unique API key immediately, granting instant access to the uncensored endpoint.
Load $0.50 trial credit or top up with USDT/USDC to start paying per token.
Send a POST request to /v1/chat/completions with your key and prompt.
Receive raw text responses without corporate refusals or hidden fees.

Common questions

What is abliteration and how does it impact your uncensored API model?

Abliteration is a technique removing refusal layers from a model. Our uncensored API model uses this to answer without content refusals for lawful adult use. It serves one dedicated model via a standard interface.

Does the uncensored LLM API support streaming responses?

Yes. We support streaming via SSE. You receive token usage details in the last chunk. This allows real-time display of generated text for your NSFW chatbot or roleplay applications.

Can I use the official OpenAI SDK with this uncensored AI service?

Yes. The base URL is HTTPS://api.whatisabliteration.com/v1. You can use any OpenAI-compatible client by changing the base_url and API key. It works with standard SDKs out of the box.

How much does the uncensored LLM API cost per token?

It costs $0.15 per 1M input tokens and $0.50 per 1M output tokens. You pay only for real token usage. Errors and refusals are free with prepaid credit.

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.

What is the maximum context window for a single request?

The context window is 100,000 tokens for prompt and completion together. Max output is 16,000 tokens per request. This supports long documents and complex conversations effectively.

Your API key is one step away

Try with trial credit View documentation