Uncensored LLM API
Dolphin nsfw: The Uncensored API Alternative
Switch to an uncensored LLM via our OpenAI-compatible API for adult content. Get a $0.50 trial, 100,000 token context, and zero subscription fees starting now.
- 100,000 token context window
- Zero monthly subscription fees
- Crypto top-ups only
Send one test request
curl https://api.dolphinnsfw.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Generate a 500 word scene of two dolphins mating at sunset"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.dolphinnsfw.com/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.dolphinnsfw.com/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
Feature overview
OpenAI Compatible
Drop-in replacement for existing clients using standard endpoints.
True Uncensored
No refusals for lawful adult, fictional, or controversial topics.
Privacy First
Prompts are not used for training your data.
Function Calling
Full support for tools, tool_choice, and JSON mode.
Streaming SSE
Real-time token usage with streaming via Server-Sent Events.
No Card Needed
Start instantly with Google login or email credentials.
Setup guide
Create Account
Sign up with Google or email to get your key.
Add Crypto Credit
Top up with USDT or USDC to start using the API.
Call Endpoints
Send requests to /v1/chat/completions and receive uncensored text.
Built with this API
Adult Content Generation
Generate unrestricted NSFW text for creative writing or chatbots.
Local Model Hosting
Access the uncensored model without managing your own GPU servers.
Developer Integration
Integrate seamlessly into your existing app using standard SDKs.
Privacy-Focused Chatbots
Build chatbots that do not train on your user prompts.
Moving from another OpenAI-compatible provider in three steps
Update your base URL and API key to switch providers in seconds.
First, navigate to the Get API key page and sign in with Google or email. Second, copy the new credential from the dashboard. Third, update your SDK configuration to point to HTTPS://api.dolphinnsfw.com/v1. The same client code works immediately. No code changes required for function calling or streaming.
How this differs from a typical alternative on 4-6 concrete signs
We strip corporate bloat to give you direct access to an uncensored model without vendor lock-in. Our API charges $0.15 per million input tokens and $0.50 per million output tokens, with no hidden fees.
dolphin NSFW: Uncensored Text Generation for Adult Use
Generate unrestricted text with a model tuned for adult themes, avoiding sudden refusals for lawful content.
NSFW Chatbot
Build conversational agents that maintain context without sanitizing dialogue.
Uncensored LLM Writer
Create long-form stories using the 100,000-token window for consistent narratives.
NSFW API Integration
Swap your base URL to our endpoint and keep your existing client code working immediately.
How it works: From signup to first token
Start by signing up with Google or email to get your key instantly. Then top up via crypto to activate credits. Send a request to our OpenAI-compatible endpoint. The model returns uncensored text immediately. No waiting, no complex setup.
What developers actually ask about this topic
Uncensored means lawful adult content passes through without refusal, except for minors. The model id is "uncensored". Context limits are 100,000 tokens with a 16,000 token output cap. Billing uses prepaid crypto credit; errors cost nothing. Streaming via SSE works for real-time token output. Function calling and JSON mode are supported. Refusals only apply to specific hard limits regarding children. This is a pure text API.
Who uses it, in which real situations; and plainly who it is NOT for
Developers building NSFW chatbots, adult content writers, and researchers testing boundary conditions use this uncensored LLM for unrestricted text generation.
It suits projects needing long outputs up to 16,000 tokens without corporate filters blocking lawful adult themes.
- Not for teams requiring image, audio, or video generation.
- Not for users needing embeddings or fine-tuning capabilities.
- Not for those requiring SLA guarantees or ISO certifications.
Common questions
What is dolphin NSFW and how does it differ from standard models?
It is an uncensored LLM API designed for adult text generation. Unlike filtered alternatives, it answers without refusing lawful topics. You access it via standard OpenAI-compatible endpoints, ensuring your existing client code works immediately with zero configuration changes.
Is there a monthly subscription fee for this uncensored LLM service?
No. We charge strictly per token usage with no monthly base fee. Input tokens cost $0.15 per million, and output tokens cost $0.50 per million. Errors and refusals incur no charge, and your prepaid credit never expires.
How do I top up my credit using cryptocurrency?
We accept only USDT on the TRC20 network or USDC on the Base network. You can deposit any whole amount between $20 and $500. Bonuses apply automatically: 5% for $50, 10% for $100, and 15% for $200.
Which payment methods do you accept?
Crypto only: USDT on TRC20 or USDC on Base, any whole amount from $20 to $500. Bonus credit applies from $50.
Does the uncensored model support streaming for real-time chat applications?
Yes. The API supports Server-Sent Events (SSE) for streaming responses. Token usage data is included in the final chunk of the stream. This allows you to build low-latency chat interfaces that feel responsive to end-users writing complex stories.
What are the limits on request size and frequency?
You are limited to 300 requests per minute and eight concurrent requests per key. Each request body must not exceed 8 MB. The model supports a context window of 100,000 tokens, allowing for substantial input and output generation per call.
Generate your API key
Sign up, copy the key, update the base URL. That is all there is to it.
