Uncensored LLM API
Uncensored LLM API for nsfw chat Integration
Integrate a raw, content-tolerant language model into your application with a standard OpenAI-compatible endpoint. No refusals for lawful adult content, no complex routing, just text in and text out.
- OpenAI-compatible POST endpoint
- No refusals for lawful adult topics
- $0.25 per 1M input tokens
Try it in one request
curl https://api.nsfwchat.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.nsfwchat.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.nsfwchat.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);- $0.25
- per 1M input tokens
- $1.00
- Output tokens / 1M
- 64,000
- token context
- $0.50
- trial credit
- 300
- requests per minute
What you get
Standard Integration
Works with official OpenAI SDKs and any OpenAI-compatible client. Change your base_url and API key to start generating text immediately.
Streaming & Tools
Supports streaming via SSE, function calling with tools, and JSON mode. Control output with temperature, top_p, and seed parameters.
Large Context Window
Handle up to 64,000 tokens per request. Generate up to 16,000 tokens in a single response without interruption.
Simple Pricing
Pay only for real token usage. Errors and refusals are free. Prepaid credit never expires, with no monthly subscription fees.
Crypto Top-Up
Top up with USDT (TRC20) or USDC (Base) from $10 to $500. Get bonus credit on larger deposits without entering a credit card.
Private & Direct
Your prompts are not used for training. Get immediate access with a Google login or email, without phone verification or delays.
How it works
Get Your Key
Sign up with Google or email and receive your API key instantly.
Add Credits
Top up with crypto to start generating, or use your trial balance.
Integrate
Point your SDK to our base URL and start streaming responses.
What people build with it
Content-Heavy Apps
Build chat applications that need to handle adult themes without unexpected refusals. Ideal for roleplay or creative writing platforms where standard models often trigger safety filters.
API-First Development
Integrate an uncensored model into your existing backend without building a custom UI. Use the standard chat-completions endpoint for consistent behavior.
Streaming Responses
Deliver real-time token streams to your users using SSE. Perfect for maintaining user engagement in long-form text generation scenarios.
Function Calling
Use tools and tool_choice to let the model interact with your system. Generate structured JSON output for reliable programmatic integration.
Why Uncensored Matters
Standard language models often refuse content that is perfectly lawful, such as mature themes or controversial topics. This uncensored LLM API is tuned to answer without these refusals, making it ideal for developers building nsfw chat applications or content-tolerant platforms. You get direct access to an open-weight model that prioritizes generation over politeness.
The model does not block lawful adult, fictional, or security-research content. However, it does enforce a hard limit: sexual content involving minors is always refused. This ensures your application remains compliant while avoiding the frustration of arbitrary content blocks during creative writing or roleplay scenarios.
OpenAI-Compatible API
We provide a raw, OpenAI-compatible chat-completions API endpoint. You can use the official OpenAI SDKs or any client that supports the OpenAI format. Simply change the base_url to our endpoint and provide your API key. This allows you to integrate an uncensored AI api into your existing infrastructure with minimal code changes.
The endpoint supports POST /v1/chat/completions and GET /v1/models. It does not offer embeddings, image generation, or fine-tuning. If you need those features, this API nsfw solution is not the right fit. For now, we focus on high-volume, content-tolerant text generation.
Developer Features
Our API supports streaming via Server-Sent Events (SSE), allowing you to deliver tokens in real-time. You can also use function calling with tools and tool_choice to enable the model to interact with your backend. JSON mode is available for generating structured data, ensuring reliable parsing in your application.
Control the output with parameters like temperature, top_p, stop, seed, presence_penalty, and frequency_penalty. The model handles a 64,000-token context window, with a maximum output of 16,000 tokens per request. This makes it suitable for long-form content generation and complex conversation history.
Pricing & Limits
We charge $0.25 per 1M input tokens and $1.00 per 1M output tokens. Errors and refusals are free. There are no monthly subscriptions or hidden fees. Prepaid credit never expires, so you only pay for what you use. Top up with crypto only: USDT (TRC20) or USDC (Base) from $10 to $500. You get a 5% bonus on $50 deposits and 10% on $100.
Each API key is limited to 300 requests per minute and 8 concurrent requests. The request body must be under 8 MB. You get one active key per account; generating a new key replaces the old one. This is not for you if you need SLA guarantees, SOC2 certification, or multi-model routing.
Questions and answers
Is this API really uncensored?
Yes, the model is tuned to answer without refusing lawful adult, fictional, or controversial topics. It does not have the same strict safety filters as consumer chat apps. The only hard limit is that sexual content involving minors is always refused.
How do I pay for the API?
You can top up your account using crypto: USDT (TRC20) or USDC (Base). We accept amounts from $10 to $500. We do not accept credit cards, PayPal, or bank transfers. Prepaid credit never expires and errors are free.
What is the context window size?
The model supports a 64,000-token context window, which includes both the prompt and the completion. You can generate up to 16,000 tokens in a single request. If you do not set max_tokens, the default output is 2,048 tokens.
Can I use this with the OpenAI SDK?
Yes, our endpoint is OpenAI-compatible. You can use the official OpenAI SDKs by changing the base_url to https://api.nsfwchat.cc/v1 and providing your API key. It works with any client that supports the OpenAI format.
Do you offer a free trial?
Yes, every new account gets $0.50 of trial credit valid for 7 days. No credit card is needed to start. You can sign up with Google or email and get your API key immediately.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
