Free and Open LLM
Uncensored LLM API for developers
Access an uncensored model for lawful adult use via the standard OpenAI API. Immediate integration with open-source code and predictable pricing.
- 'Uncensored' model with no refusals
- OpenAI SDK compatible
- Prepaid credit that never expires
Try in a single request
curl https://api.apisemrestricoes.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.apisemrestricoes.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.apisemrestricoes.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);- $0.25
- per 1M input tokens
- $1.00
- Output tokens / 1M
- 100,000
- token context
- $0.50
- free trial credit
- 300
- requests per minute
What you get
Full Compatibility
Use the same OpenAI SDKs and clients. Change only the base URL and API key to start sending requests immediately.
Wide Context Window
Support for 100,000 tokens combining prompt and completion. Ideal for processing long documents and extensive conversations without cuts.
Streaming and Functions
Native support for Server-Sent Events (SSE) for real-time responses. Function calling included for automation.
Guaranteed Privacy
Your prompts are not used to train models. Create your account with just an email and password, no phone number required.
Single and Simple Key
One key per account, regenerable at any time. No complexity of multiple tokens or granular permissions to get started.
Bonus Credits
Minimum top-up of $10. Earn +5% extra credit when topping up $50 or +10% when topping up $100, with no hidden monthly fees.
How it works
Create Your Account
Enter email and password on the registration page to generate your API key instantly.
Configure the SDK
Update the base URL to our endpoint and enter your key in your existing OpenAI client settings.
Send Requests
Start sending prompts to the 'uncensored' model and receive generated text without the usual restrictions.
What people build with it
Adult Content Generation
Create stories, scripts, or texts with mature themes without the risk of content censorship blocks. Perfect for creators who need narrative freedom.
Security Research
Test prompt resilience in LLMs without the model refusing controversial or technical topics by default. Ideal for jailbreak analysis.
RPG and Interactive Fiction
Maintain immersion in roleplay games with characters that react naturally to adult themes and conflicts without generic warnings.
Textual Data Analysis
Process large volumes of text while maintaining full context. The 100k token context window allows deep analysis of long documents.
What our API is
Our unrestricted API is a hosted service exposing a single open-weight large language model (LLM). Unlike platforms offering multiple models or multimodal features, we focus on delivering high-quality text with zero content filters. The 'uncensored' model runs on our own GPU servers and is designed to respond to lawful adult topics, security research, and controversies without the default refusals found in commercial models.
The model is not GPT, Claude, Gemini, or any other brand. It is an independent, open, and transparent implementation. You send text and receive text. No surprises with model changes or silent updates that alter system behavior without your notice.
OpenAI Compatibility
For developers already familiar with the OpenAI ecosystem, integration is trivial. We use the standard /v1/chat/completions endpoint and support streaming via Server-Sent Events (SSE) and function calling. If you have Python or Node.js code configured for the OpenAI API, just change the base_url to https://api.apisemrestricoes.com/v1 and enter your new key.
This eliminates the learning curve and lets you leverage the client infrastructure you already master. The JSON response structure follows the expected standard, making it easy to drop-in to existing projects that need more content freedom.
No Censorship, No Surprises
The term 'uncensored' means the model does not refuse adult, fictional, or politically sensitive topics by default. This is crucial for applications where pre-censorship breaks the user experience or research accuracy. The only strict, always-applied restriction is sexual content involving minors, which will be consistently blocked.
We do not promise corporate SLAs, SOC2 certifications, or 99.99% availability. We are a direct-to-developer service for those who value content freedom over bureaucratic guarantees. If you need a model that responds exactly as the prompt dictates, without convenience filters, this is the right place.
Who should NOT use it
This API is not for you if you need image, audio, or video generation, as we provide text only. It is also not ideal for those expecting multiple model options or intelligent routing between different LLMs. If you require specific medical (HIPAA) or government compliance, our standard infrastructure may not meet your audit requirements.
Additionally, if you need embeddings for vector databases or custom fine-tuning, our current offering is limited to chat completions. This service is for those who want simplicity, content freedom, and predictable cost, without the complexity of giant ecosystems.
Frequently asked questions
Does the API support response streaming?
Yes, the <code>/v1/chat/completions</code> endpoint supports Server-Sent Events (SSE). You can enable streaming by setting the appropriate parameter in your SDK client to receive tokens in real time.
Are my data used to train the model?
No. Privacy is a priority. Your prompts and completions are not used to train our infrastructure models. You create the account with just an email and password.
What happens if I exceed the rate limit?
The limit is 300 requests per minute per key. If you exceed this rate, you will receive an exceeded limit error. You can regenerate your key at any time to get a new one, but the limit applies per active key.
How does payment work and do credits expire?
The model is prepaid with credit that never expires. You can top up from $10 using cryptocurrency (USDT or USDC). Bonus credits are added automatically on larger top-ups.
Is there a free trial period?
Yes, each new account receives $0.50 of free trial credit valid for 7 days. No credit card or phone number is required to access this initial credit.
Your key is one form away
Create an account, copy the key, and change the base URL. That is all the configuration.
