EN ▾

Limitless LLM API.

Start with free trial credit

With email and password, the key appears on screen immediately.

Get API key
Base URL
https://api.sansursuzapi.com/v1
Model
uncensored

Direct Text API

uncensored AI API key for private text generation

A lightweight and fast LLM API designed for pure text generation, instead of unnecessary censorship and complex features. Full control and transparent pricing for developers and content creators.

Get API keyRead documentation

  • OpenAI SDK compatible architecture
  • 300 requests/minute limit
  • Pay as you go

Try with one request

curl https://api.sansursuzapi.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."}]
  }'
$0.25per 1M input tokens
$1.00completion tokens / 1M
100,000token context window
$0.50free trial credit
300requests per minute

What you get

OpenAI Compatible Architecture

Use existing OpenAI SDKs and clients directly. Complete your integration in seconds by configuring only base_url and API key.

Pure Text Focus

No unnecessary loads like image or audio generation. Only text input and text output. This focus allows the API to run faster and lighter.

Large Context Window

Process long texts and documents in a single request with a 100,000-token context window. Covers total prompt and completion token count.

Security and Tool Calling

Create dynamic and real-time responses with smart function calling (tool/function calling) and streaming support via SSE.

Full Privacy

Only email and password are needed to create an account. Your inputs are not used for training and your data is not tracked.

Transparent Pricing

No monthly fixed fee. Pay as you go. With the prepaid credit system, your balance never expires.

How it works

Get Your API Key

Register with email and password and get your key immediately.

Configure Connection

Set https://api.sansursuzapi.com/v1 as base_url and your API key in your own code.

Send First Request

Create a POST request using "uncensored" as the model ID and start receiving responses.

What people build

Automated Content Generation

Automate high-volume text generation workflows for blog posts, articles, or marketing copy. Censorship mechanisms do not interrupt your content flow.

Data Classification and Analysis

Build analytics systems that process large datasets and generate structured text. The model interprets complex contexts with fewer constraints.

Dynamic Chatbots

Build bots that respond in real time for customer service or game NPCs. Improve user experience with streaming support.

Research and Prototyping

Create rapid prototypes for new LLM integrations. Its OpenAI-compatible structure minimizes switching costs.

Unlimited Content Generation

The uncensored AI API removes the virtual censorship imposed by standard large language models, providing more direct responses. Our model is specifically tuned for legal adult content. If your content includes political, philosophical, or adult-themed topics, the model does not filter or warn about them unnecessarily. This ensures content creators and developers do not experience unexpected interruptions during text generation.

Our model is a model like GPT, Claude, Gemini, or other large data providers. It is an open-weight model running on our own GPU servers. This independent structure allows your content to be less restricted by external sources. The only exception is sexual content involving minors within legal limits; such requests are always blocked. Everything else is fully free in your production process.

OpenAI-Compatible Architecture

Our API exactly mimics OpenAI's chat-completions endpoint. This means you can use your existing libraries and SDKs (Python, Node.js, etc.) directly. The POST /v1/chat/completions endpoint comes with streaming (SSE) and function calling (tool calling) support. The GET /v1/models endpoint returns the list of available models. There are no additional features like image or audio generation; this reduces the load per request and latency.

curl https://api.sansursuzapi.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."}]
  }'

Use https://api.sansursuzapi.com/v1 as the base URL. Send "uncensored" as the model ID. This simple structure shortens your integration time and minimizes technical complexity.

Privacy-Focused Infrastructure

We respect your personal data. You do not need a phone number or credit card to create an uncensored AI account. An email address and password are sufficient. You generate your API key immediately and start using it. Your inputs (prompts) are not used for model training, and your privacy is protected.

There is one API key per account. You can generate a new key at any time to invalidate the old one. This is a fast method to minimize security vulnerabilities. Details such as server location or GPU provider are hidden to reduce complexity; our focus is solely on text generation quality.

Fast Integration for Developers

Our API is designed for developers who build rapid prototypes. The 100,000 token context window allows you to process long documents in a single pass. With tool calling support, you can connect your API to functions you write yourself. With streaming (SSE) support, you can provide instant text flow to your users.

from openai import OpenAI

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

After creating your API key, you only need to add base_url and key to your code. This standard approach ensures seamless operation with libraries in different languages. With our quick start guide, you can send your first requests in minutes.

Transparent Pricing

No monthly subscription. We operate on a pay as you go system. We charge $0.25 per 1M input tokens and $1.00 per 1M output tokens. Your balance is loaded as prepaid credit and never expires. The minimum top up amount is $10. You earn 5% bonus credit on deposits of $50 or more, and 10% bonus credit on deposits of $100 or more. Payment options include cryptocurrency (USDT or USDC).

New accounts are offered a $0.50 trial credit valid for 7 days. No card information is required. Limits are fixed: 300 requests per minute and a maximum request body of 8 MB. These limits apply for fair use and cannot be increased.

Frequently Asked Questions

How do I create my API key?

Go to the 'Get Your API Key Now' page on the homepage. Register with email and password. Your key is displayed immediately and ready for use. No phone or card information is required.

What technology does your model use?

Our model is not GPT, Claude, or Gemini. It is an open-weight model running on our own GPU servers. It is specifically tuned and provides uncensored responses for legal adult content.

How large is the context window?

The context window is 100,000 tokens. This covers both prompt and completion tokens. It is ideal for long texts and documents.

Are my inputs used for training?

No, your inputs are not used for training. Your privacy is paramount. You create an account with just an email and password, and your data is protected.

Who should not use this API?

This API is for text generation only. If you want image, audio, or video generation, or need embedding and fine-tuning features, this service is not for you. It is also not optimized for enterprise customers seeking high SLA guarantees or ISO certification.

Your key is as long as a form

Create an account, copy the key, and change the base URL. Setup is that simple.

Get API key