Uncensored LLM API

Apertus app: uncensored LLM API

Get an uncensored AI app API with 100,000 token context windows, streaming, and transparent crypto billing for developers who need raw compute without vendor lock-in.

100,000 token context window
$0.15 per 1M input tokens
OpenAI compatible endpoints

Create key View documentation

Test with a single API call

curl https://api.apertusapp.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Run curl test with empty headers"}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://api.apertusapp.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.apertusapp.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

Capabilities

OpenAI Compatible
Use standard OpenAI SDKs with our base URL and API key for immediate integration.
Large Context
Process up to 100,000 tokens in the combined prompt and completion window.
Streaming Support
Receive real-time token updates via Server-Sent Events with usage data in the final chunk.
Function Calling
Enable tools and tool_choice parameters for structured output and external data retrieval.
JSON Mode
Force strict JSON responses using the response_format parameter for reliable parsing.
Prepaid Credits
Pay only for tokens used with no expiration on your prepaid credit balance.

Integration guide

Create Account
Sign up with Google or email to receive your API key instantly.
Add Credits
Top up with USDT or USDC to start sending requests immediately.
Send Request
Point your client to our base URL and generate uncensored text.

Developer use cases

Content Generation
Generate uncensored creative writing without artificial content filters blocking your narrative.
Research Analysis
Process large documents with the 100k context window for deep analysis.
App Integration
Embed the API into your WordPress site or custom application easily.
Dev Testing
Test function calling and JSON modes with our standard compatible endpoints.

apertus app: the uncensored LLM API

apertus app delivers a single, high-capacity uncensored LLM API for developers who need raw text generation without vendor routing complexity. We charge only for actual token usage at transparent rates, ensuring no idle fees.

Direct Integration

Connect your existing stack using standard OpenAI-compatible endpoints. Send prompts and receive text outputs with zero configuration overhead.

Content Flexibility

The model answers without refusals for lawful adult content. You get full control over the output style.

Predictable Costs

Prepaid credit never expires. Pay $0.15 per million input tokens and $0.50 per million output tokens.

Visit the Get API key page and sign in with Google or an email address.
Receive your unique API key instantly. No phone number required.
Top up with crypto if needed, or start with the free $0.50 trial credit.
Set your base URL to HTTPS://api.apertusapp.com/v1 in your OpenAI-compatible SDK.
Send a POST request to /v1/chat/completions with model ID uncensored.

Built for developers, not roleplay bots

This API serves developers integrating uncensored LLMs into applications. It delivers raw token compute via an OpenAI-compatible endpoint, not a chat interface. You get function calling, JSON mode, and streaming via SSE. We do not offer roleplay bots or a dedicated chat website. This is infrastructure for your software, not a conversational UI for casual users.

Why we are not a typical model aggregator

We charge only for tokens your prompt and completion actually consume, ignoring idle time. Aggregators often route through multiple vendors or charge for idle time. We offer a single, high-capacity, unfiltered text-generation model at a flat, transparent rate. Unlike typical aggregators, we do not bundle unused capabilities. Our prepaid credit never expires. You pay for what you use.

Feature	Typical Aggregator	Apertus
Pricing Model	Complex tiers or idle fees	Flat rate per token
Model Routing	Multiple vendors	Single uncensored model
Expiry	Monthly subscription	Credit never expires

Migrate from OpenAI or OpenRouter in minutes

Switch your integration by updating one base URL and swapping your API key. Our uncensored LLM API uses the exact same OpenAI-compatible endpoints for chat completions and models. You get 100,000 token context with transparent token-only pricing. No complex routing layers or vendor lock-in. Just point your SDK to our endpoint and start generating uncensored responses immediately.

Real questions from developers about uncensored AI

Can I use this uncensored AI app for image generation? No, Apertus is strictly a text-only API. It does not support embeddings, audio, video, or image creation, so if you need to automate image generation inside your app, you must integrate a separate service. The model id is simply 'uncensored', which you send via the standard OpenAI-compatible /v1/chat/completions endpoint. This ensures you get raw token compute without routing fees or extra model layers, keeping your integration simple and direct.

Common questions

What is the apertus app API key and how do I get one?

You get one by signing up with Google or email. The key appears immediately on the dashboard. No phone number is required. You can generate a new key to replace the old one at any time via your account settings.

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.

Is the uncensored LLM model the same as GPT or Claude?

No. It is an open-weight model run on our own servers. It is NOT GPT, Claude, Gemini, Grok, DeepSeek, Qwen, Llama or any other vendor's model. It answers without content refusals for lawful adult use.

How much does the uncensored AI cost per token?

Input tokens cost $0.15 per million. Output tokens cost $0.50 per million. Errors and refusals are free. You only pay for the tokens your prompt and completion actually consume with our prepaid credit that never expires.

Can I use streaming with the uncensored chatbot API?

Yes. Streaming is supported via Server-Sent Events (SSE). Token usage details are included in the last chunk of the stream. You can also use function calling, JSON mode, and standard parameters like temperature and top_p.

What is the maximum context window for the uncensored AI models?

The context window is 100,000 tokens for prompt and completion together. The maximum output is 16,000 tokens per request. If you do not set max_tokens, the limit defaults to 2,048 tokens for the completion.

Your API key is ready

Create key

Apertus app: uncensored LLM API

Capabilities

OpenAI Compatible

Large Context

Streaming Support

Function Calling

JSON Mode

Prepaid Credits

Integration guide

Create Account

Add Credits

Send Request

Developer use cases

Content Generation

Research Analysis

App Integration

Dev Testing