Uncensored LLM API, pay per token
Apertus: an independent guide and a drop-in alternative
Apertus provides a transparent, prepaid API for an uncensored large language model. Use our OpenAI-compatible endpoint to get text responses without content refusals or monthly subscriptions.
- Pay only for tokens used
- Uncensored lawful content
- Crypto top-ups only
Try it in one request
curl https://api.apertus.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."}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.apertus.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)import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.apertus.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);- per 1M input tokens
- $0.25
- Output tokens / 1M
- $1.00
- token context
- 64,000
- trial credit
- $0.50
- requests per minute
- 300
What you get
OpenAI Compatible
Drop in your existing code by changing the base URL and API key. We support the standard /v1/chat/completions endpoint with streaming, JSON mode, and function calling.
Uncensored Generation
The model answers without refusing lawful adult, fictional, or controversial topics. We only block sexual content involving minors, ensuring broad creative freedom.
Prepaid Credit
No monthly fees or tier locks. You pay $0.25 per 1M input tokens and $1.00 per 1M output tokens. Credit never expires and errors are free.
Crypto Billing
Top up with USDT (TRC20) or USDC (Base) in whole amounts from $10 to $500. Get bonus credit on larger deposits with no credit card required.
High Capacity
Support a 64,000 token context window with up to 16,000 tokens per output. Ideal for long documents, code generation, and complex reasoning tasks.
Developer First
Sign up with Google or email to get an API key instantly. No phone number needed, and your prompts are not used for training.
How it works
Get Your Key
Sign up via Google or email to receive your API key immediately.
Top Up Crypto
Add credit using USDT or USDC to start using the API.
Integrate & Run
Update your base URL and start sending requests to the uncensored model.
What people build with it
Creative Writing
Generate stories, scripts, and roleplays without content filters blocking mature themes. Use the uncensored model to explore creative boundaries freely.
Data Extraction
Parse large documents or codebases using the 64k context window. Get structured JSON outputs reliably for your backend pipelines.
Research & Analysis
Ask controversial questions or analyze sensitive topics without default refusals. Ideal for security research and diverse content moderation testing.
Custom Agents
Build AI agents that use tools and function calling without interruption. Integrate easily with existing OpenAI SDKs for robust automation.
Why Apertus?
Apertus is an independent API provider focused on one thing: delivering an uncensored large language model via a standard interface. Unlike major vendors that lock you into complex tiers or restrict lawful content, we offer a single dedicated model tuned for open generation. You pay only for the tokens you use, with no monthly subscription fees. Our billing is transparent and prepaid, so you always know your exact cost. We do not claim to be GPT, Claude, or any other vendor; we are a standalone service running our own open-weight model on dedicated servers. This approach ensures consistent performance and predictable pricing for developers who need reliability without corporate bloat.
OpenAI Compatible Interface
Our API follows the OpenAI chat-completions standard, making integration trivial. You simply update the base URL to https://api.apertus.top/v1 and provide your API key. The model ID is "uncensored". We support streaming via Server-Sent Events, JSON mode for structured outputs, and function calling with tools. The context window is 64,000 tokens, allowing you to process large inputs while generating up to 16,000 tokens per request. If you need to switch from another provider, the code changes are minimal. We do not offer embeddings, image generation, or audio processing, keeping the interface focused on high-quality text generation.
- POST /v1/chat/completions
- GET /v1/models
- Streaming, JSON mode, and tools
Uncensored & Lawful
Our model is tuned to answer without content refusals for lawful adult use. This means you can generate fiction, explore controversial topics, or conduct security research without hitting arbitrary filters. We do not encourage illegal activity, and we maintain one hard limit: sexual content involving minors is always blocked. This ensures we remain compliant while offering maximum freedom for creative and professional use cases. The model does not distinguish between GPT, DeepSeek, or other vendors; it is a distinct open-weight model optimized for responsiveness and lack of bias. You get direct text input and output, with no hidden moderation layers interfering with your workflow.
Transparent Prepaid Pricing
We charge $0.25 per 1M input tokens and $1.00 per 1M output tokens. Credit is charged based on real token usage, and errors or refusals are free. There are no subscriptions, no monthly fees, and no tier locking. Your prepaid credit never expires, so you can use it whenever you need it. This model is ideal for developers who want predictable costs without paying for idle capacity. We are not the right choice if you need a free unlimited tier, SLA guarantees, or multi-model routing. We also do not offer on-prem deployment or certified data privacy for regulated industries like HIPAA. Our focus is on simple, uncensored text generation at a fair price.
Questions and answers
Is Apertus the official site for GPT or Claude?
No. Apertus is an independent service running its own uncensored model. We are not affiliated with OpenAI, Anthropic, or any other vendor. We simply use the same API interface for easy integration.
How do I pay for the API?
We accept crypto only: USDT (TRC20) or USDC (Base). You can top up any whole amount from $10 to $500. We do not accept credit cards, PayPal, or bank transfers. New accounts get $0.50 trial credit with no card needed.
Does the credit expire?
No, your prepaid credit never expires. You can use it whenever you need it. If you make a mistake like a double charge, contact support to fix it. Errors in your requests are free.
What is the context window size?
The model supports a 64,000 token context window, including both the prompt and the completion. You can generate up to 16,000 tokens in a single request. If you do not set max_tokens, the default output is 2,048 tokens.
Can I use this for commercial projects?
Yes, you can use the API for any lawful purpose. The model is uncensored and does not restrict adult or controversial content. We do not use your prompts for training, ensuring your data remains private.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
