Uncensored API Guide

Dolphin llm online uncensored API guide

Access the dedicated Dolphin uncensored model via our openai compatible API with a massive 100k context window for NSFW content creation and reliable development without monthly fees.

100k token context window
Crypto-only prepaid billing
No monthly subscription fees

Claim trial key View documentation

$0.15per 1M input tokens
$0.50Output tokens / 1M
100,000token context
$0.50trial credit
300requests per minute

Test with one API call

base_url: https://api.dolphinllmonline.com/v1
model: uncensored

curl https://api.dolphinllmonline.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list all endpoints"}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://api.dolphinllmonline.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.dolphinllmonline.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);

Platform capabilities

OpenAI Compatible

Works with any standard OpenAI SDK by changing the base URL.

100k Context

Process large documents with a 100,000 token combined input and output window.

Crypto Top-ups

Fund your account with USDT or USDC and receive bonus credits automatically.

Streaming Support

Get real-time token responses via Server-Sent Events for lower perceived latency.

JSON Mode

Force structured output using the response_format parameter for reliable parsing.

No Subscriptions

Pay only for tokens used with prepaid credit that never expires.

Setup process

1
Create Account
Sign up with Google or email to get your API key instantly.
2
Buy Crypto Credit
Top up with USDT or USDC to receive your bonus credits.
3
Start Coding
Point your SDK to our base URL and send requests immediately.

Common use cases

NSFW Story Generation

Generate unrestricted creative writing without content filters blocking adult themes.

Large Document Analysis

Process entire codebases or books within the 100k context window.

Chatbot Backend

Build reliable backend services using standard OpenAI compatible endpoints.

Data Extraction

Extract structured data from text using strict JSON response formatting.

Who needs the Dolphin uncensored API and who should skip it

NSFW creators and developers need the Dolphin uncensored API for unrestricted text generation without content refusals.

Use it for lawful adult fiction or security research.
Skip it if you need image or embedding capabilities.

This dedicated uncensored LLM serves one model with a 100k context window. It is not for generic chatbots requiring multiple model routing or strict enterprise SLAs. Use our OpenAI compatible API endpoint for direct integration.

dolphin LLM online: use cases for NSFW and creative writing

The Dolphin uncensored API handles adult themes without arbitrary refusals, making it ideal for unrestricted creative workflows.

NSFW Fiction Generation

Create detailed adult narratives with consistent tone and explicit detail, avoiding standard safety filters that cut off content prematurely.

Creative Writing Tools

Build writing assistants that explore controversial topics freely, ensuring your draft retains your original voice without censorship interruptions.

Roleplay Scenarios

Run immersive character bots that maintain personality and context across long conversations, leveraging the 100k token window for deep continuity.

Developers ask: latency, context limits, and SDK compatibility

Latency scales with context window and request volume, while SDK compatibility remains strict to the standard /v1/chat/completions interface. We support a massive 100k token context window, allowing you to process large datasets without complex chunking strategies. Streaming via SSE ensures you receive tokens immediately, which is critical for real-time applications. Our API handles function calling and JSON mode natively, so your existing OpenAI-compatible code works out of the box. No extra configuration is needed.

Sign up. Use Google or email to create an account. No phone number required. Receive a trial credit instantly.
Get your key. The system displays your API key immediately. Copy it securely.
Add crypto credit. Top up with USDT (TRC20) or USDC (Base). Payments start at $20. Receive bonus credits automatically.
Make requests. Send POST requests to /v1/chat/completions. Use the standard OpenAI SDK. Your first token arrives in seconds.

Checklist: choosing the right uncensored LLM provider

Verify critical constraints before committing your workflow. Ensure the provider offers a 100k context window for long documents, supports streaming via SSE for real-time token delivery, and allows JSON mode for structured outputs. Confirm billing is prepaid with no monthly lock-in, as this avoids unexpected charges. Check if the API key is generated instantly upon signup. Finally, confirm crypto-only top-ups like USDT TRC20 to maintain privacy. Avoid providers that route through third-party proxies, as this adds latency and cost to your requests.

Migrate from another OpenAI-compatible provider in 3 steps

Switch your existing client configuration in minutes. First, create an account and retrieve your unique API key. Second, update your base_url to HTTPS://api.dolphinllmonline.com/v1 and inject the key. Third, set the model parameter to "uncensored". This endpoint accepts standard OpenAI-compatible requests without code changes. You immediately gain access to a 100k context window and prepaid token billing.

Frequently asked questions

What is the dolphin LLM online API?

It is a hosted, OpenAI-compatible endpoint serving the uncensored model. You send text and receive text via standard HTTP requests. The base URL is HTTPS://api.dolphinllmonline.com/v1. It supports streaming, JSON mode, and function calling for flexible integration.

How much does the uncensored API cost?

Input tokens cost $0.15 per million, and output tokens cost $0.50 per million. Errors and refusals are free. You pay only for real usage from your prepaid credit. There are no monthly fees or subscription traps.

Can I use the standard OpenAI SDK?

Yes, it is fully compatible with the official OpenAI SDK. You just change the base URL to our endpoint and provide your API key. It supports streaming via SSE, function calling, and all standard parameters like temperature and top_p.

What is the context window size?

The model supports a 100,000 token context window. This includes both prompt and completion tokens together. The maximum output per request is 16,000 tokens, or 2,048 if you do not set the max_tokens parameter explicitly.

How do I pay for the API?

We accept crypto only: USDT on TRC20 or USDC on Base. Minimum top-ups start at $20. You receive bonus credit of 5% to 15% depending on your deposit amount.

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.

Get your API key instantly

Claim trial key