Uncensored OpenAI-compatible API

Dolphin LLM: uncensored LLM online and through an API

Dolphin LLM provides a single, hosted uncensored AI model via a standard OpenAI-compatible interface, allowing you to bypass content filters without managing local GPU infrastructure.

Get API key Read the docs

OpenAI-compatible chat API
100,000 token context window
Pay-as-you-go pricing

Try it in one request

curl https://api.dolphinllm.com/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.dolphinllm.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.dolphinllm.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);

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

What you get

Drop-in Compatibility

Use your existing OpenAI SDKs by simply changing the base URL and API key. No custom integrations required.

Uncensored Generation

The model is tuned to answer without content refusals for lawful adult use, including controversial or explicit topics.

No Training on Prompts

Your prompts are not used for training your data. We prioritize privacy for your creative and research work.

Streaming Support

Get real-time responses via Server-Sent Events (SSE) for smoother user experiences in your applications.

Function Calling

Support for tool and function calling allows you to integrate the model into complex workflows.

Simple Billing

Prepaid credit never expires. Add funds via crypto (USDT on TRC20, USDC on Base) with bonus credits for larger top-ups.

How it works

Get Your Key

Update Your Client

Point your OpenAI-compatible client to https://api.dolphinllm.com/v1 and insert your key.

Start Generating

Send requests to the /v1/chat/completions endpoint with the model ID 'uncensored'.

What people build with it

Creative Writing

Generate stories and scripts without sudden refusals for mature themes or unconventional narrative structures. Write freely without filtering out bold ideas.

Data Extraction

Parse large documents or logs using the 100,000 token context window. Extract insights from long texts without losing context.

Research & Analysis

Ask about controversial topics or security research without the model hedging its answers. Get direct responses to complex queries.

Chat Applications

Build chatbots that feel more human and less restricted. Stream responses for a natural conversation flow.

What is Dolphin LLM?

Dolphin LLM is an independent service providing a single, high-quality uncensored large language model. Unlike multi-model gateways, we focus on one optimized open-weight model served via a standard OpenAI-compatible interface. This simplicity ensures predictable behavior and consistent quality without the complexity of routing or model selection. The model is tuned to answer without content refusals for lawful adult use, making it ideal for users who want unrestricted text generation without the hassle of managing local GPU infrastructure.

OpenAI-Compatible Interface

Our API mirrors the standard OpenAI chat-completions endpoint structure. You can use the official OpenAI SDKs or any compatible client by changing the base URL to https://api.dolphinllm.com/v1 and providing your API key. The endpoint supports POST /v1/chat/completions for standard requests and streaming via Server-Sent Events (SSE). It also supports tool and function calling for advanced integrations. We do not offer embeddings, image, audio, or video generation, keeping the service focused on text.

Uncensored & Abliterated

The core value of Dolphin LLM is its ability to generate content without the typical refusals found in models like GPT or Claude. It is an open-weight model tuned for unrestricted creative use, including lawful adult themes and controversial topics. While it does not over-explain or prioritize politeness over output, it remains a general-purpose model. A hard content limit always applies: requests involving sexual content with minors are blocked. For most other topics, the model provides direct, unfiltered responses.

Who This Is NOT For

If you need a variety of specialized models, different embedding dimensions, or image generation, this API is not for you. We do not offer SLA guarantees, SOC2/HIPAA certifications, or on-prem deployment options. Users requiring a free, unlimited tier with no credit system will find our prepaid model less suitable. Additionally, if you need a model that strictly adheres to mainstream corporate content policies and avoids any mature themes, our uncensored focus may be too permissive for your use case.

Questions and answers

Is Dolphin LLM an official OpenAI product?

No, Dolphin LLM is an independent service. We serve our own open-weight model, not GPT-3.5, GPT-4, or any other OpenAI model. However, our API interface is compatible with the standard OpenAI SDKs, allowing you to switch by changing the base URL and API key.

What does 'uncensored' mean exactly?

It means the model is tuned to answer without content refusals for lawful adult use, controversial topics, or creative writing. It does not impose the same politeness or topic restrictions as mainstream models. The only hard limit is that sexual content involving minors is blocked.

Do you use my prompts for training?

No. We prioritize privacy. Your prompts are not used for training the model. You can use the API for confidential creative work or research without worrying about your data being ingested into the model's weights.

How does the pricing work?

We use a pay-as-you-go prepaid credit system. There are no monthly fees or subscriptions. You pay $0.15 per 1M input tokens and $0.50 per 1M output tokens. Credits never expire, and you can add funds via crypto (USDT on TRC20, USDC on Base).

Can I try it for free?

Yes. New users get $0.50 of trial credit valid for 7 days, one per person. Claim this credit with one click on your API key page. No credit card is needed to start. You can sign up with just an email and password to 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.

Get API key

Guides

Practical articles on setup, pricing and integration.

How to Run Dolphin LLM: Local Setup vs Hosted APIHow to run Dolphin LLM on your own hardware with Ollama or llama.cpp, what memory it needs, and when a hosted OpenAI-compatible endpoint is the…

Dolphin LLM API: Local, Rented GPU or HostedThree ways to call a Dolphin-style uncensored model over an API: run it locally, rent a GPU, or use a hosted OpenAI-compatible endpoint. Costs and…

Free LLM API for Developers: Trial vs Pay as You GoLooking for a free API to build with? See what the $0.50 trial buys, what prepaid pay-per-token costs in real requests, and when a free tier falls…

Open WebUI API Endpoints: Connect an Uncensored LLMSet up Open WebUI with an OpenAI-compatible uncensored LLM API: base URL, key, model ID, Docker variables, a curl test and fixes for common errors.

How to Use an LLM Without Login for Instant AccessDiscover how to use an LLM without login hurdles. Get instant API access to the uncensored Dolphin LLM with just an email. No phone, no card…

All guides →