OpenAI-Compatible API

Uncensored AI API: Open and Filter-Free LLM Model

Q: Do I need a credit card to use the API?

No for the trial. The $0.50 free trial credit is granted with just an email and password, no card required. For top ups above the free amount, we accept crypto (USDT or USDC).

Q: Are my training data used in the API?

No. Privacy is key. Your prompts and responses are not used to train or improve the base model. Your account requires only an email and password.

Integrate an open, filter-free, and uncensored LLM model into your application in minutes.

OpenAI-compatible Base URL
Single 'uncensored' model
Credit never expires

Get API key Read documentation

per 1M input tokens: $0.25
Output tokens / 1M: $1.00
token context: 100,000
trial credit: $0.50
requests per minute: 300

Try in a single request

curl https://api.apiiasemcensura.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.apiiasemcensura.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.apiiasemcensura.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);

What you get

Native Compatibility

Use your favorite clients and SDKs. The API follows the OpenAI standard with identical base URL and endpoints.

Real Uncensored

The model responds to adult, controversial and creative topics without artificial refusals, except for content involving minors.

Transparent Pricing

Pay only for what you use. No monthly fees, no subscriptions. Prepaid credit that never expires.

Streaming and Tools

Full support for streaming via SSE and tool/function calling for fast, interactive responses.

Guaranteed Privacy

Your prompts are not used to train the model. Create an account with email and password.

High Context Window

Process up to 100,000 tokens per request, ideal for long documents and conversation history.

How it works

Create Your Account
Enter email and password on the registration page to get your API key immediately.
Configure the SDK
Update your library's base_url to the API endpoint and enter your key.
Make Your First Call
Send a POST request to /v1/chat/completions with the 'uncensored' model.

What people build with it

Immersive Roleplay

Keep the character's persona without the model breaking context due to content judgments. Ideal for long, complex narratives.

Adult Text Generation

Produce fiction or NSFW content without arbitrary barriers. The model understands nuances and avoids unnecessary refusals.

Stress Testing

See how an LLM reacts to controversial or technical topics without the bias of standard moderators.

Research Applications

Analyze sensitive or historical data without the risk of content filtering based on platform policy.

Full OpenAI Compatibility

Our uncensored AI API is built to be plug-and-play. You don't need to learn new syntax or handle complex routing. Just change the base_url in your existing OpenAI client to point to our service. The /v1/chat/completions endpoint responds exactly as you expect, keeping the standard JSON structure. This means popular libraries like LangChain, LlamaIndex and the official SDK work without deep modifications.

We don’t offer a fleet of varied models or intelligent routing between providers. We focus on one thing: delivering the best uncensored open model with the reliability of a standard API. If you already know how to use the OpenAI API, you already know how to use ours.

Uncensored LLM Model with Zero Content Filters

The core of our offering is an open-weight language model running on our own GPU servers. It is fine-tuned to not refuse topics considered adult, controversial, or creative. Unlike large proprietary models that may 'break' a character's personality in roleplay when they sense a censorship trigger, our model maintains narrative consistency.

It is important to note that there is a strict limit: sexual content involving minors is blocked. For everything else, including adult fiction, fictional violence, and philosophical debates, the model responds directly. It is not GPT, Claude, or any other third-party model; it is an independent model optimized for freedom of expression in legal applications.

Fair Pricing and No Subscriptions

No surprise monthly fees here. The model is pay as you go with prepaid credit. You pay $0.25 per 1 million input tokens and $1.00 per 1 million output tokens. The credit you add never expires, allowing you to use it whenever you want, no rush.

To get started, a minimum top up of $10 is required, accepting cryptocurrencies (USDT or USDC). If you top up larger amounts, you receive a bonus: 5% extra from $50 and 10% extra from $100. There is no unlimited free tier for continuous use, but every new account receives $0.50 of free trial credit valid for 7 days, no credit card required.

Who Should NOT Use This API

This solution is not for you if you need image, audio, or video generation, or if you require semantic embeddings. We also do not offer custom fine-tuning or SLA guarantees (such as 99.99% uptime). If your application depends on HIPAA or SOC2 certifications for strict medical or financial compliance, this service may not be suitable. Additionally, if you need multiple specialized models (one for translation, another for code) routed automatically, our API focused on a single uncensored model may be too simplistic for your complex needs.

Frequently asked questions

Do I need a credit card to use the API?

Not for the trial. The $0.50 trial credit is granted with just email and password, no card required. For top-ups above the free amount, we accept cryptocurrencies (USDT or USDC).

Is my training data used in the API?

No. Privacy is paramount. Your prompts and responses are not used to train or improve the base model. Your account requires only email and password.

What is the token and context limit?

The model supports a context window of 100,000 tokens, combining prompt and response. This allows processing long documents and maintaining extensive conversation histories.

Can I use streaming in the response?

Yes. The API supports streaming via Server-Sent Events (SSE), allowing you to display the response token by token in real time, improving the end-user experience.

What happens if you exceed the request limits?

The limit is 300 requests per minute per API key. If you hit the request body limit (8 MB), the request will be rejected. Each account has a key that can be regenerated at any time.

Your key is a form away

Create an account, copy the key, and change the base URL. That's all the configuration.

Get API key