OpenAI-compatible uncensored LLM API for devs.

Uncensored Chatgpt: an independent guide and a drop-in alternative

Get a single, high-performance uncensored LLM via the standard OpenAI-compatible endpoint. No web app, no model routing—just tokens.

64k context window, no refusals
Crypto-only billing, no cards
300 RPM per key, $0.25/1M in

Get API key Read the docs

Try it in one request

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

per 1M input tokens: $0.25
Output tokens / 1M: $1.00
token context: 64,000
trial credit: $0.50
requests per minute: 300

What you get

Standard Endpoint

Use POST /v1/chat/completions with any OpenAI SDK. Just change the base_url and API key to start sending requests immediately.

Uncensored Model

The model id 'uncensored' answers without content refusals for lawful adult use. It is not GPT, Claude, or any other vendor's model.

Crypto Billing

Pay only for real token usage with USDT (TRC20) or USDC (Base). Prepaid credit never expires, and errors are free.

Streaming & Tools

Supports streaming via SSE, function calling, and JSON mode. All standard parameters like temperature and top_p are available.

Developer First

Clear Limits

300 requests per minute per key with an 8MB body limit. One active key per account keeps your integration simple.

How it works

Sign Up

Top Up

Add prepaid credit using USDT or USDC via crypto.

Integrate

Point your existing OpenAI-compatible client to our endpoint.

What people build with it

NSFW Content Generation

Generate unrestricted adult content for creative writing or art pipelines without worrying about standard filters blocking lawful output.

Automation Scripts

Power backend automation with a reliable text-in, text-out API that handles edge cases without human-like refusals.

Data Processing

Use the model for large-context data extraction or summarization where a 64k token window reduces the need for chunking.

Research & Testing

Test LLM behavior on controversial topics or security prompts in a controlled environment with transparent token billing.

The Uncensored API Advantage

Most 'uncensored' options are web chat interfaces or aggregators that route between multiple models. We provide a single, high-performance uncensored model via a standard OpenAI-compatible API. This means you get consistent behavior without the latency of model routing or the UI overhead of a web app. Our model is tuned to answer without content refusals for lawful adult use, making it ideal for NSFW applications that need reliable text generation.

You pay only for real token usage. Errors and refusals are free, and prepaid credit never expires. This crypto-only billing model removes the friction of monthly subscriptions or credit card declines. You get a direct line to the model you need, without managing infrastructure or waiting for support tickets.

OpenAI-Compatible Integration

Our API uses the standard POST /v1/chat/completions endpoint. This allows you to integrate instantly with existing SDKs by simply changing the base_url and providing your API key. The model id is uncensored, an open-weight model run on our own servers. It is not GPT, Claude, Gemini, Grok, DeepSeek, Qwen, Llama, or any other vendor's model.

We support streaming via SSE, function calling, and JSON mode. All standard parameters like temperature, top_p, stop, seed, and penalties are available. The context window is 64,000 tokens, allowing you to process large inputs in a single request. Max output is 16,000 tokens, or 2,048 if you do not set max_tokens.

Model Capabilities & Limits

This is a text-only API. We do not offer embeddings, image, audio, or video generation. There is no fine-tuning or model routing. You get one uncensored large language model for text in and text out. This simplicity ensures predictable performance and pricing without the complexity of multi-model aggregators.

Rate limits are set to 300 requests per minute per key, with a maximum of 8 concurrent requests. Request bodies are limited to 8 MB. Each account has one active key; generating a new key replaces the old one. A hard content limit applies: sexual content involving minors is always refused. Prompts are not used for training, and privacy is maintained with just an email address.

Who This Is NOT For

If you need image generation, audio processing, or embeddings, this API is not the right choice. We do not offer SLA guarantees, SOC2/HIPAA certifications, or on-prem deployment options. This is not a web chat app for end-users; it is a developer-focused API for integration. If you need model routing between different vendors or a free unlimited tier, look elsewhere. We provide a single, high-performance model for developers who want direct access without web app overhead.

Questions and answers

Is this the official OpenAI ChatGPT?

No. We provide an independent, open-weight model that is compatible with the OpenAI API format. It is not GPT-3.5, GPT-4, or any other OpenAI model. It is a separate model tuned for uncensored responses.

What payment methods do you accept?

We accept crypto only: USDT (TRC20) or USDC (Base). You can top up any whole amount from $10 to $500. We do not accept credit cards, PayPal, or bank transfers. Prepaid credit never expires.

Do I need a credit card for the trial?

No. Every new account gets $0.50 of trial credit valid for 7 days. You can sign up with Google or email and password without providing a phone number or card.

How is billing calculated?

You pay $0.25 per 1M input tokens and $1.00 per 1M output tokens. You are charged only for real token usage; errors and refusals are free. Credit is prepaid and never expires.

What is the context window size?

The model supports a 64,000 token context window for prompt and completion combined. The maximum output per request is 16,000 tokens, or 2,048 if you do not set the max_tokens parameter.

Your key is one form away

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

Get API key