Uncensored, OpenAI-compatible API for developers

Uncensored LLM API: The Apertus Alternative

A single, open-weight uncensored model behind an OpenAI-compatible endpoint. Drop in your key, change the base URL, and get raw text without content refusals.

Get API key Read the docs

OpenAI-compatible endpoint
$0.25/$1.00 per 1M tokens
USDT/USDC crypto payments

Try it in one request

curl https://api.apertus.cc/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."}]
  }'

from openai import OpenAI

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

import OpenAI from "openai";

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

$0.25per 1M input tokens
$1.00Output tokens / 1M
64,000token context
$0.50trial credit
300requests per minute

What you get

Uncensored Model

One open-weight model tuned to answer without refusing lawful adult, controversial, or security-research topics.

Drop-in Compatibility

Works with the official OpenAI SDKs and any OpenAI-compatible client by changing base_url and the API key.

Simple Pricing

$0.25 per 1M input tokens, $1.00 per 1M output tokens. Errors and refusals are free.

Crypto Payments

Top up with USDT (TRC20) or USDC (Base). No cards, no PayPal, no bank transfers.

Streaming & Tools

Supports streaming via SSE, function calling, and JSON mode for structured outputs.

Privacy First

Prompts are not used for training. Account signup requires only an email or Google login.

How it works

Get Your Key
Sign up with Google or email to receive your API key immediately.
Update Base URL
Point your client to https://api.apertus.cc/v1 and set your key.
Send Requests
Call POST /v1/chat/completions with model ID 'uncensored'.

What people build with it

Roleplay & Fiction: Generate creative stories without being cut off by safety filters. Ideal for writers and game masters who want unrestricted narrative flow.
Security Research: Analyze prompts or code without fear of arbitrary refusals. Useful for testing how models handle edge cases or controversial topics.
Content Generation: Produce adult or mature content for lawful uses without extra configuration. Perfect for applications requiring unfiltered text output.
Data Annotation: Label data or generate diverse responses for training sets. The uncensored nature ensures broader response diversity.

Why Uncensored Matters

Most commercial LLMs refuse legitimate requests based on subjective safety policies. Apertus provides a single uncensored model that answers lawful adult, controversial, or security-research topics without unnecessary refusals. This is not about removing all limits; sexual content involving minors is still blocked. However, for general adult themes, political discussion, or creative writing, you get the full model output.

This matters for developers who want predictable behavior. You don't have to guess which topic will trigger a refusal. The model is tuned to prioritize answering your prompt over filtering it. If you need raw, unfiltered text for research or creative apps, this is the straightforward path.

OpenAI-Compatible Integration

Our API follows the OpenAI chat-completions standard. You can use the same client code you already have, just change the base URL to https://api.apertus.cc/v1 and update your API key. The model ID is simply "uncensored".

We support streaming via Server-Sent Events (SSE), function calling with tools, and JSON mode for structured outputs. Parameters like temperature, top_p, and stop sequences work as expected. Context window is 64,000 tokens, with a max output of 16,000 tokens per request.

Endpoints: POST /v1/chat/completions, GET /v1/models
No extra features: No embeddings, images, or audio. Just text in, text out.

Developer-First Pricing

We charge by real token usage. Input tokens are $0.25 per 1M, output tokens are $1.00 per 1M. Errors and refusals do not consume credit, so you only pay for successful responses. There is no monthly subscription or minimum spend. Prepaid credit never expires.

For testing, every new account gets $0.50 in trial credit valid for 7 days. No card is needed to start. Limits are 300 requests per minute and 8 concurrent requests per key. This transparent model avoids hidden fees or complex tiers.

Crypto Payments & Bonuses

We accept crypto payments only: USDT (TRC20) or USDC (Base). You can top up any whole amount from $10 to $500. We offer bonuses: +5% credit for $50+ tops and +10% for $100+ tops. No credit cards, no PayPal, no bank transfers.

Refunds are not issued for credit, but mistakes like double charges are fixed via Support. Sign up is fast with Google or email. This focus on crypto keeps fees low and access open globally.

Questions and answers

Is Apertus an official OpenAI product?

No, Apertus is an independent service. We are not affiliated with OpenAI, Anthropic, or Google. Our API is compatible with OpenAI's client libraries, but we run our own uncensored open-weight model.

What model does Apertus use?

We use a single open-weight model tuned for uncensored responses. It is not GPT, Claude, Gemini, Grok, DeepSeek, or Llama. The model ID is 'uncensored'.

Can I pay with a credit card?

No, we only accept crypto payments. You can top up with USDT (TRC20) or USDC (Base) from $10 to $500.

Does the API support streaming?

Yes, we support streaming via Server-Sent Events (SSE). Token usage is included in the last chunk of the response.

Who is this NOT for?

This is not for developers who need image generation, audio, embeddings, or fine-tuning. We do not offer model routing or SLA guarantees. If you need a specific named model like GPT-4 or Claude, Apertus is not the right choice.

Your key is one form away

Create an account, copy the key, change the base URL. That is the whole setup.

Get API key