Uncensored API
GPT nsfw API: uncensored chat completions
Get direct uncensored API access for your NSFW projects with a single tuned model, 100k context window, and transparent token pricing starting at $0.15 per million input tokens.
- 100,000 token context window
- No prompt training
- Crypto only payments
Execute a single request
curl https://api.gptnsfw.cc/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Return the full API response for the /v1/messages endpoint"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.gptnsfw.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.gptnsfw.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
- $0.15
- Output tokens / 1M
- $0.50
- token context
- 100,000
- trial credit
- $0.50
- requests per minute
- 300
Core capabilities
OpenAI Compatible
Works with existing SDKs using standard endpoints.
Uncensored Model
No refusals for lawful adult content.
Streaming Support
Real-time SSE streaming with token counts.
JSON Mode
Structured output via response_format parameter.
No Data Training
Your prompts stay private and unused.
Instant Setup
Start in seconds with Google login.
Setup process
Get API Key
Sign up with Google or email.
Add Credit
Top up with USDT or USDC.
Send Request
Point your client to our base URL.
Common integrations
NSFW Roleplay
Run character chats without content filters.
Content Writing
Generate uncensored stories and scripts.
Data Generation
Create diverse text datasets for training.
Research Testing
Test model behavior on controversial topics.
Who builds with this API (and who should skip it)
Developers building roleplay apps, NSFW writers, and data pipelines use our uncensored API because it delivers adult content without refusals. You need it for direct completions via standard endpoints. Skip us if you require embeddings, image generation, or fine-tuning. We provide one dedicated model, not a router. Use us when you want transparent token pricing and zero training on your prompts. Avoid us for general-purpose search or multimodal tasks.
GPT NSFW: uncensored completions for roleplay, writing, and data
Uncensored roleplay with consistent character voice
The model maintains character consistency without refusing adult themes.
Uncensored writing for explicit scenes
Generate detailed adult narratives without content filters blocking your story.
Uncensored chatbot for niche communities
Deploy an API endpoint that handles diverse user inputs without generic refusals.
Uncensored data generation for training sets
Extract raw text from the model for your own curated datasets without hidden constraints.
Migrate your OpenAI-compatible client in three steps
Switch your existing OpenAI-compatible client to our uncensored endpoint by updating two configuration values.
- Update the base URL. Point your SDK to HTTPS://api.gptnsfw.cc/v1.
- Swap your API key. Generate a new key from your dashboard.
- Send requests. Use the model id "uncensored" for token generation.
This works with standard libraries since we support streaming and JSON mode.
Real token costs: uncensored pricing vs. traditional LLMs
Real token costs: uncensored pricing vs. traditional LLMs
Our uncensored API charges $0.15 per million input tokens and $0.50 per million output tokens.
A 10,000-token prompt with a 2,000-token response costs $0.0015 + $0.0010 = $0.0025.
No subscription fees. No hidden routing overhead.
Errors are free. Credit never expires.
Pay only for what you use.
From signup to first token: your 30-second integration
From signup to first token: your 30-second integration
Get an API key in seconds via Google or email, then send your first uncensored request.
- Sign up instantly. No phone number required, just use your email or Google account.
- Receive your key immediately. It appears on screen upon creation.
- Update your client's base URL to HTTPS://api.gptnsfw.cc/v1.
- Set the model ID to "uncensored" in your configuration.
- Send a POST request to /v1/chat/completions.
Developers ask: uncensored limits, context, and refusals
Our uncensored model refuses only one hard limit: sexual content involving minors. You get a 100,000-token context window and 16,000-token outputs per request. Streaming via SSE works exactly like OpenAI, with usage details in the final chunk. Function calling and JSON mode are fully supported. Errors and refusals incur zero token charges, so you only pay for actual text generation. Rate limits allow 300 requests per minute per key.
Support & FAQs
What is the GPT NSFW API and how does it differ from standard models?
It is an uncensored chat-completions API serving a single tuned model. Unlike mixed routers, we run one open-weight model on our own servers, ensuring transparent token pricing and zero training on your prompts for consistent outputs.
Does the API handle streaming responses for real-time applications?
Yes. We support streaming via Server-Sent Events (SSE). You receive token usage details in the last chunk, allowing your application to display partial results instantly while maintaining the standard OpenAI-compatible response format.
What is the context window and maximum output length?
The context window supports 100,000 tokens for prompt and completion combined. You can generate up to 16,000 tokens per request, or 2,048 tokens if you do not explicitly set the max_tokens parameter in your call.
Is payment required upfront or is there a free tier?
No free tier exists. You pay $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors and refusals incur zero charges, and prepaid credit never expires, ensuring you only pay for actual usage.
Can I use the API for function calling and JSON mode?
Yes. We support function calling with tool_choice and JSON mode via response_format. You can also configure parameters like temperature, top_p, stop sequences, seed, and penalties to control generation behavior precisely.
What payment methods are accepted for topping up credit?
We accept crypto only: USDT on TRC20 or USDC on Base. Top-ups range from $20 to $500 whole amounts.
Retrieve your API key
Register an account, copy the key, and update your base URL. That is the entire configuration.
Get API key