Uncensored LLM API for developers.

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

A direct, OpenAI-compatible endpoint for developers needing an uncensored LLM API without content filters. Get your API key in seconds and start generating text with zero refusals for lawful adult content.

OpenAI-compatible chat-completions endpoint
Crypto payments, prepaid token credits
64k context window, single uncensored model

Get API key Read the docs

Try it in one request

curl https://api.nsfwchatgpt.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.nsfwchatgpt.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.nsfwchatgpt.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

Drop-in Compatibility

Works with official OpenAI SDKs by changing base_url to https://api.nsfwchatgpt.cc/v1. No custom libraries needed for basic integration.

Uncensored Output

The 'uncensored' model does not refuse lawful adult, fictional, or controversial topics. Only sexual content involving minors is strictly blocked.

Developer Features

Supports streaming via SSE, function calling, and JSON mode. Use parameters like temperature, top_p, and stop for precise control.

Transparent Pricing

Pay only for real token usage: $0.25/1M input and $1.00/1M output tokens. Errors and refusals are free.

Crypto Top-ups

Fund your account with USDT (TRC20) or USDC (Base). Minimum $10, no cards or PayPal. Bonus credits available on larger deposits.

Simple Limits

300 requests per minute and 8 concurrent requests per key. One active key per account, replaced if you generate a new one.

How it works

Get Your Key
Sign up with Google or email and password to receive your API key immediately.
Add Crypto Credit
Top up your account with USDT or USDC to start making requests.
Send Requests
Point your OpenAI-compatible client to our base URL and start generating text.

What people build with it

Adult Content Generation

Build NSFW chatbots or story generators without hitting content filters. Ideal for applications requiring unrestricted creative writing or roleplay.

Security Research

Analyze model behavior without refusals blocking your prompts. Use the uncensored LLM API to test edge cases and jailbreaks effectively.

Indie AI Apps

Deploy character-driven AI applications where personality matters more than politeness. Avoid the 'polite refusal' loop in user conversations.

Data Training Prep

Generate large volumes of diverse text data for fine-tuning or training other models. Use the API to create varied datasets quickly.

OpenAI-Compatible & Uncensored

Our nsfw chatgpt API provides a hosted, OpenAI-compatible chat-completions endpoint serving a single uncensored large language model. Text in, text out. The base URL is https://api.nsfwchatgpt.cc/v1, which works with the official OpenAI SDKs and any OpenAI-compatible client by changing base_url and the API key. The model ID to send is "uncensored". It is an open-weight model run on our own servers, tuned to answer without content refusals for lawful adult use. It is NOT GPT, Claude, Gemini, Grok, DeepSeek, Qwen, Llama or any other vendor's model.

The context window is 64,000 tokens (prompt + completion together), with a max output of 16,000 tokens per request (2,048 if max_tokens is not set). Features include streaming via SSE, function calling, and JSON mode. We do not offer embeddings, image, audio or video generation, or fine-tuning. A hard content limit always applies: no sexual content involving minors.

Developer-First Integration

We focus on developer utility: transparent token pricing, crypto payments, and standard SDK compatibility. Unlike content-aggregators, we provide a direct, code-first API integration. You get a single active key per account, with a limit of 300 requests per minute and 8 concurrent requests. The request body is limited to 8 MB. Errors and refusals are free, so you only pay for real token usage.

POST /v1/chat/completions
GET /v1/models

No phone number is required for signup. You can continue with Google or use email and password. The key is shown immediately. This is an API for developers, not a chat website or app.

Transparent Token Pricing

Pricing is straightforward: $0.25 per 1M input tokens and $1.00 per 1M output tokens. Prepaid credit is charged by real token usage. No subscription, no monthly fee. Paid credit never expires. Mistakes such as a double charge are fixed through the Support page, but credit is not refunded.

Top-ups are crypto only: USDT (TRC20) or USDC (Base). Any whole amount from $10 to $500 is accepted. You get a +5% bonus credit from $50 and +10% from $100. No cards, no PayPal, no bank transfer. Every new account gets $0.50 of trial credit valid for 7 days. No card needed for the trial.

Who This Is NOT For

This API is not for you if you need image, audio, video, or embedding generation. We do not offer model routing between vendors, fine-tuning, or SLA percentages. We do not claim SOC2, HIPAA, or ISO certifications. If you need on-prem deployment, a team of named customers, or benchmark scores, this is not the right fit. We are an independent service, not an official partner of any major AI vendor. We serve one model, not a marketplace. If you need a chat website or app with a UI, look elsewhere; we provide the API endpoint for your own applications.

Questions and answers

Is this the official ChatGPT API?

No. We are an independent service providing an uncensored LLM API. The model ID is "uncensored", an open-weight model on our servers. It is not GPT-4 or any other OpenAI model. We are compatible with the OpenAI API format but serve a different model.

How do I pay for the API?

Payments are crypto only. You can top up with USDT (TRC20) or USDC (Base). Minimum amount is $10. No credit cards, PayPal, or bank transfers are accepted. Trial credit does not require a card.

What is the context window size?

The context window is 64,000 tokens for prompt and completion combined. The maximum output per request is 16,000 tokens. If you do not set max_tokens, the limit is 2,048 tokens.

Does the API support streaming?

Yes, streaming is supported via SSE. Token usage is included in the last chunk. You can also use function calling and JSON mode for structured outputs.

Is my data used for training?

No, prompts are not used for training. Privacy is respected. An account needs only an email, and no phone number is required.

Your key is one form away

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

Get API key