Uncensored AI
Uncensored LLM API for Text Generation
Access an uncensored LLM via the standard OpenAI protocol. No corporate content blocks, a 100k context window, and transparent per-token pricing.
- 100k token uncensored model
- Compatible with the official OpenAI SDK
- Trial credit without a credit card
Try with a request
curl https://api.apisinrestricciones.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.apisinrestricciones.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.apisinrestricciones.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's included
Full Compatibility
Use the official OpenAI library by changing only the base_url. Supports streaming (SSE) and tool/function calling without code modifications.
Proprietary Model
We run 'uncensored', an open-weight model on our GPU servers. It is not GPT, Claude, or Gemini; it is a model designed not to deny adult or controversial content.
Clear Pricing
$0.25 per 1M input tokens and $1.00 for output. No monthly subscriptions or hidden fees. Prepaid credit never expires.
Real Privacy
We do not use your prompts to train other models. You only need an email and password; no phone number or credit card required for the trial.
No False Promises
Text only. We do not generate images, audio, or video. No fine-tuning or embeddings. It is a pure text API.
Clear Limits
300 requests per minute per key. However, we strictly block sexual content involving minors.
How it works
Create Your Account
Sign up with an email and password to get your API key instantly.
Configure Your SDK
Point your OpenAI client to our base_url and add your key.
Send Your Prompt
Call the /v1/chat/completions endpoint and receive uncensored text.
What you can create
NSFW Content Generation
Ideal for applications requiring adult narrative without artificial blocks. Perfect for interactive story platforms or roleplay.
Security Research
Get direct answers to controversial or technical topics without the usual corporate 'filter'. Useful for drafting analysis.
Bot Development
Integrate AI into Discord or Telegram without worrying about the platform's automatic moderation. Total control over the tone.
Rapid Prototyping
Test the reasoning capabilities of an uncensored model without long-term subscription commitments. Pay as you go.
What is an API Sin Restricciones?
An unrestricted API offers a language model that does not apply the content filters typical of major tech companies. Our service exposes a single uncensored model, optimized to respond to adult, controversial, or creative topics without refusing by default. Unlike generalist platforms, there are no surprises here: you send text and receive text generated by an open model hosted on our servers.
The key is transparency. We don't sell promises of 'advanced reasoning' or 'unlimited creativity'. We sell direct access to a model that does what you ask, within basic legal limits (such as the strict prohibition of child sexual abuse material). It is the perfect tool if you are tired of your API returning 'Not safe for general audiences' for a simple mention.
Simple Integration with the OpenAI SDK
Our uncensored AI works via the same protocol used by GPT-4. You only need to adjust the base_url and the api_key in your existing code. This allows developers already using the OpenAI infrastructure to migrate instantly to an uncensored model without rewriting their entire business logic.
We support streaming via Server-Sent Events (SSE) and function calling, maintaining the standard chat/completions structure. This means you can use clients like LangChain or LlamaIndex with minimal adjustments. You don't need to learn a new syntax; you just change the AI source.
- Endpoint:
POST /v1/chat/completions - Model:
uncensored - Support: Streaming and Tool Calling
100k Context Uncensored Model
The model we serve has a context window of 100,000 tokens. This allows processing long documents, long chat histories, or full code in a single request. Unlike other providers that limit context memory to reduce costs, here the capacity is part of the standard product.
It is important to clarify that this is not a Google, Anthropic, or X model. It is an open-weight model fine-tuned by us to maximize instruction adherence without predefined moral filters. If you need image, audio, or video generation, this is not your API; it is exclusively for text.
Who is this API NOT for?
Although our uncensored AI API is powerful, it is not suitable for all use cases. If you need guaranteed 99.9% SLAs, HIPAA or SOC2 certifications for sensitive medical or financial data, or if you require fine-tuning of your own models, this service is not for you. It is also not ideal if you need multiple models via an intelligent router or native image generation.
It is perfect for independent developers, NSFW content creators, and research teams that prioritize response freedom over corporate uptime guarantees. If your priority is strict automatic moderation of every word that comes out, you probably prefer the big platforms. Here, you decide what to do with the text.
Frequently Asked Questions
What type of content do you block?
We strictly block sexual content involving minors. Everything else, from nudity to controversial political topics or explicit language, is allowed. We do not apply corporate 'sensitivity' filters.
Do I need a credit card for the trial?
No. You can register with just an email and password. You receive $0.50 in credit valid for 7 days to test the API without needing to link any payment method.
Can I use the official OpenAI library?
Yes. You just need to change the <code>base_url</code> variable to <code>https://api.apisinrestricciones.com/v1</code> and use your API key. Everything else in the code, including streaming and tool calling, works the same.
Are my data used to train models?
No. Privacy is fundamental. Your prompts and responses are not used to train other models on the platform. We only keep the data necessary for billing and service operation.
How many requests can I make per minute?
The limit is 300 requests per minute per API key. The maximum request body size is 8 MB. This is sufficient for the vast majority of chat and text generation applications.
Your key is one step away
Create an account, copy the key, and change the base URL. That's it.
