Uncensored LLM API

Unrestricted API: The Uncensored LLM for Code-First Integration

Get an unrestricted, open-weight model via a hosted OpenAI-compatible API. Integrate uncensored generation into your code without managing GPUs or dealing with refusal filters.

Get API key Read the docs

OpenAI SDK compatible
No content refusals
Crypto payments only

Try it in one request

curl https://api.unrestricted.cc/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.unrestricted.cc/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.unrestricted.cc/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

64,000token context

$0.50trial credit

300requests per minute

What you get

OpenAI-Compatible Interface

Use standard endpoints like /v1/chat/completions with existing SDKs. Change base_url and API key to connect instantly to our uncensored infrastructure.

Raw Uncensored Output

The model answers without blocking lawful adult, controversial, or security topics. It is an independent open-weight model, not a resold GPT or Llama variant.

Developer-First Controls

Access streaming via SSE, JSON mode, function calling, and standard sampling parameters like temperature and top_p for precise integration.

Transparent Token Pricing

Pay only for what you use. Input tokens are $0.25 per million; output tokens are $1.00 per million. Errors are free.

Simple Crypto Top-ups

Fund your account with USDT (TRC20) or USDC (Base). No credit cards, no PayPal, no monthly subscriptions. Credit never expires.

Generous Context Window

Supports 64,000 tokens context and up to 16,000 tokens output per request. Ideal for long-document processing and complex code generation.

How it works

Create Account
Sign up with Google or email to receive your API key instantly without phone verification.
Fund Your Wallet
Top up with crypto (USDT or USDC) to activate your balance, or start with $0.50 trial credit.
Integrate & Query
Point your OpenAI SDK to our base URL and start sending requests to the uncensored model.

What people build with it

Uncensored Coding Assistant

Generate code without hallucinated constraints or refusal blocks blocking technical explanations. Ideal for developers needing raw output for complex logic without filter interference.

Content Generation at Scale

Produce unrestricted creative writing, reviews, or analysis for lawful adult or niche topics. Avoid the variability of local GPU setups with a stable hosted stream.

Security Research & Red Teaming

Probe models for vulnerabilities without hitting standard safety filters prematurely. Get unfiltered responses to edge-case prompts for accurate security assessment.

Data Annotation & Labeling

Use the uncensored model to label data without bias from commercial safety layers. Ensure your pipeline gets consistent, unmoderated text outputs.

What is an Unrestricted LLM?

An unrestricted llm is a large language model tuned to remove or significantly reduce the safety filters that block certain topics, styles, or outputs. Unlike consumer chat wrappers that may refuse to answer questions about adult themes, controversial politics, or specific medical advice, an uncensored model prioritizes answering the prompt based on its training data.

Our uncensored ai model is an open-weight variant hosted on our servers. It is not GPT, Claude, or Llama; it is a distinct model designed to answer without content refusals for lawful adult use. This makes it ideal for developers who want raw model behavior without the overhead of running GPUs locally.

OpenAI-Compatible API Endpoints

We provide a strict, focused API that mirrors the OpenAI chat-completions interface. You can use the official OpenAI SDKs for Python, Node.js, and other languages by simply changing the base_url to https://api.unrestricted.cc/v1 and providing your API key.

POST /v1/chat/completions: Send your prompt and receive text output.
GET /v1/models: List available models.

We do not offer embeddings, image generation, audio, or video. This is a text-only API. The model ID you use is uncensored. It supports streaming via Server-Sent Events (SSE), JSON mode, and function calling, giving you full programmatic control over the output format.

Why Use an Uncensored Model?

Commercial models often refuse to answer valid questions because they trigger broad safety classifiers. An uncensored llm allows you to retrieve information or generate content without these arbitrary blocks. This is crucial for applications where you need consistent, unfiltered responses, such as in creative writing, niche content generation, or security research.

By using our hosted API, you avoid the complexity of managing GPU clusters. You get a reliable, high-availability endpoint that scales with your needs. The model is tuned to answer without refusals, ensuring that your application delivers content based on the prompt, not on a hidden policy layer.

Who This Is NOT For

This API is not for users who want a pre-built chat interface or a consumer app. We do not offer a website where you type questions and get answers; we provide the raw API for developers to build their own experiences. If you need image generation, embeddings, or real-time voice synthesis, this is not the right tool.

It is also not for users who require enterprise-grade SLAs, SOC2 certifications, or on-premise deployment. We are a lean, independent service focused on providing uncensored text generation at scale. If you need a dedicated account manager or custom model training, look elsewhere. We are for developers who want direct access to an unfiltered model via code.

Questions and answers

Is this the same as GPT-4 or Llama?

No. Our model is an independent open-weight model run on our own servers. It is not GPT, Claude, Gemini, Grok, DeepSeek, Qwen, or Llama. It is specifically tuned for uncensored output.

How do I pay for the API?

We accept only crypto: USDT (TRC20) or USDC (Base). You can top up any whole amount from $10 to $500. Credit never expires, and errors are free. No credit cards or PayPal are accepted.

What is the context window and output limit?

The model supports a 64,000-token context window (prompt + completion). You can request up to 16,000 tokens of output per request, or 2,048 tokens if you do not set max_tokens.

Can I use the OpenAI SDK?

Yes. The API is OpenAI-compatible. You can use the official OpenAI SDKs by setting the base_url to https://api.unrestricted.cc/v1 and providing your API key.

Is there a trial available?

Yes. Every new account gets $0.50 of trial credit valid for 7 days. No credit card is needed to sign up via Google or email.

Your key is one form away

Create an account, copy the key, change the base URL. That is the whole setup.