OpenAI-compatible
Use the familiar /v1/chat/completions interface. Just change the base_url and your API key in existing SDKs.
API for developers
Uncensored LLM API for maximum creativity
Use a specially tuned, uncensored LLM via a standard interface. No unexpected filters, no model selection, no surprises.
- OpenAI-compatible interface
- No filters for adult content
- $0.50 trial credit without card
Test with one request
curl https://api.unzensiertesllm.com/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.unzensiertesllm.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.unzensiertesllm.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);- $0.25per 1M input tokens
- $1.00output tokens / 1M
- 100,000token context
- $0.50trial credit
- 300requests per minute
Your benefits
Pure text API
Focus on text input and output. No overhead for images or audio, resulting in fast response times.
Large context
Process long documents effortlessly with a context window of 100,000 tokens for prompt and response.
Transparent pricing
Pay only for what you use. Purchased credit never expires, even after months of silence.
Ready to start immediately
Create your account with email and password. The API key is displayed immediately, no credit card required.
Privacy
Your prompts are not used for training. Your data remains your data.
How it works
Create account
Register with email and password and receive your API key immediately.
Top up credit
Top up credit via crypto (USDT or USDC) or use the free trial credit.
Integrate API
Connect your project to our Base URL and make your first request.
What others build with it
Adult storytelling apps
Build chat apps for romance or fantasy without the AI shying away from intimate details. Ideal for creative writing tools without censorship logic.
Critical analysis
Use the uncensored LLM for unbiased summaries of controversial topics. The AI answers directly, without moral blinders.
Role-playing
Implement character AIs for games or dating apps. The model simulates personalities authentically, even in rough or explicit scenarios.
Data analysis
Process large volumes of text for content analysis. The broad context window allows understanding long documents in context.
Why an uncensored LLM?
Many standard models are trained to be safe, which often means rejecting nuanced or adult content. Our uncensored LLM is specifically tuned to generate content without discarding it due to taboos or political correctness filters. The model answers as long as the request is legal.
This does not mean everything is allowed. Sexual content involving minors is strictly blocked. But for adult fictional content, political opinions, or medical facts, there are no artificial brakes. You get a pure text API that delivers what you ask for, not what the AI considers polite.
Seamless integration (OpenAI-compatible)
Integration requires minimal effort because we adopt the proven structure of the OpenAI API. The POST /v1/chat/completions and GET /v1/models endpoints work with the official SDKs. You only need to set the base_url to https://api.unzensiertesllm.com/v1 and provide your API key.
Streaming via SSE and sending tools (function calling) are also supported. The model is addressed with the ID uncensored. It is a standalone, open-weight model on our GPU servers, not a resale of GPT or Claude. For developers, this means code written for OpenAI continues to run here with minimal adaptation effort.
No unexpected blocks
The term 'uncensored' sounds like freedom, but it also brings responsibility. We only specifically block sexual content involving minors. Everything else – whether explicit, controversial, or blunt – is let through. This makes us the first choice for applications that need genuine emotional range or unvarnished information.
We do not offer model selection or routing between different providers. We deliver a single, optimized model. This is not a disadvantage, but a decision for consistency. You do not have to guess which model is answering. It always answers with the same, predictable, and unbiased model.
Who is this NOT the right choice for?
This API is not for you if you need multimedia content. We do not generate text, images, audio, or video. There are also no embeddings for vector search or fine-tuning options for your own model. If you need special 99.9% SLA guarantees or ISO certifications for medical compliance (HIPAA), you are in the wrong place. We are an independent service without enterprise support contracts.
Even for pure text tasks that require extremely fast latency under milliseconds, our solution might be too slow as it runs on standardized cloud servers. If you have full control over the hardware and power consumption and want to take this risk, a local model might be better. But for a fast, filter-free integration into your app, we are the more efficient solution.
Frequently Asked Questions
How fast is the response time compared to local models?
Our response times depend on server load, but are usually in the same range as cloud solutions. Local models can be faster for very short prompts because they have no network latency. However, for most use cases, the speed of our API is more than sufficient.
Is my prompt used for training?
No. Unlike some free services, we do not store your inputs to further train the base model. Your data is used exclusively to process your request.
What happens if I have used up my trial credit?
The $0.50 free trial credit expires after 7 days. You can top up at any time. There are no monthly fees binding you, even if you do not use the credit immediately.
Can I change my API key later?
Yes. You can generate a new API key in your account at any time. The old key becomes invalid immediately, increasing the security of your application if you suspect it might be compromised.
Does the API also support German?
Yes. The model is multilingual and understands and generates fluent German. The quality of the German response is comparable to English, as it is a modern, well-developed model.
