Uncensored API

Dolphin uncensored ai API guide

Get a drop-in, OpenAI-compatible API for the uncensored LLM model with a 100,000 token context window and transparent pricing starting at $0.15 per million input tokens.

100,000 token context window
$0.15 per 1M input tokens
Crypto payments only

Try with trial credit Read the docs

Try it in one request

curl https://api.dolphinuncensoredai.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List steps to deploy docker container."}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://api.dolphinuncensoredai.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.dolphinuncensoredai.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

What you get

OpenAI-Compatible

Works with your existing SDKs by changing one base URL and API key.

Large Context

Process up to 100,000 tokens in prompt and completion combined for long docs.

Streaming Support

Receive real-time token usage and text via standard Server-Sent Events (SSE) streams.

JSON Mode

Force structured outputs with the response_format parameter set to json_object for reliability.

Function Calling

Enable tool use and tool_choice for dynamic, programmatic interactions with your app.

Privacy First

Prompts are not used for training, and no phone number is required for signup.

How it works

1 / 3

Create Account

2 / 3

Top Up Credit

Add crypto funds with USDT or USDC to start using the service.

3 / 3

Send Request

Point your client to our base URL and start generating text.

What people build with it

Adult Content Generation
Create unrestricted fictional stories without sudden refusals for lawful adult topics.
Security Research
Analyze jailbreaks and prompt injection attacks with a model that does not censor.
Roleplay Applications
Build immersive chatbots that maintain character and context over long conversations.
Code Completion
Generate code snippets with fewer interruptions from content safety filters.

Get your first response in under sixty seconds by following these three straightforward steps.

Sign up: Use “Continue with Google” or an email and password on the Get API key page.
Why developers still choose uncensored models over GPT-4

Developers choose uncensored models to bypass sudden refusals and restrictive filters that break application logic during roleplay or creative writing tasks. Unlike proprietary models that may censor lawful adult content or controversial topics, our API ensures consistent responses without hidden restrictions. You get a predictable endpoint where the model answers directly, avoiding the need to debug why a request failed due to content policy. This reliability is critical for NSFW applications and niche use cases where strict compliance isn't required.

dolphin uncensored AI for roleplay, writing, and coding

The uncensored LLM powers creative workflows by refusing to filter adult themes or controversial logic in your outputs.
Roleplay & NSFW Stories
Generate unrestricted character dialogues without sudden content blocks. The model maintains persona consistency for long contexts up to 100,000 tokens.
Technical Writing
Produce detailed code explanations without sanitizing technical jargon. Use JSON mode to parse structured responses directly into your apps.
Coding Agents
Execute function calling for tool use. Stream responses via SSE to keep your UI responsive during long generation tasks.

Stop guessing: avoid common uncensored API pitfalls

Most developers waste credits by ignoring token limits or expecting image generation. Our endpoint returns only text via POST /v1/chat/completions. Set max_tokens to 16,000 to prevent truncation. Streaming via SSE requires parsing the final chunk for usage stats. We refuse requests involving minors, so filter those early. Use our 100,000-token context window wisely: prompt + completion counts together. Don’t assume unlimited output.

Migrate your OpenAI client in three simple steps

Switching to our uncensored LLM requires only three configuration changes. Update your base_url to HTTPS://api.dolphinuncensoredai.com/v1 and set your API key. Change the model ID to "uncensored" in your client settings. Verify connectivity by sending a POST request to /v1/chat/completions. Our implementation supports standard parameters like temperature and streaming via SSE. This drop-in approach lets you retain your existing code while accessing unrestricted responses without sudden filters.

The uncensored API buyer’s checklist
The uncensored API buyer’s checklist
Verify the endpoint, pricing, and limits before committing.
- Endpoint: Must be /v1/chat/completions with a clear base URL.
- Pricing: Look for transparent per-token rates, not hidden subscriptions.
- Limits: Check context windows and requests per minute.
- Payments: Prefer crypto-only options like USDT or USDC for privacy.
- Refunds: Ensure credit does not expire if unused.
- Key Management: One active key per account is standard.

Questions and answers

What is dolphin uncensored AI?

It is a hosted, OpenAI-compatible API endpoint for the uncensored large language model. The base URL is HTTPS://api.dolphinuncensoredai.com/v1. It supports streaming, function calling, and JSON mode.

How much does the API cost?

Input tokens cost $0.15 per 1M and output tokens cost $0.50 per 1M. Errors and refusals incur zero charges. Prepaid credit never expires and is charged strictly by real token usage.

Does the API support streaming responses?

Yes, it supports streaming via Server-Sent Events (SSE). Token usage details are provided in the final chunk of the stream, allowing you to monitor costs in real-time during generation.

What is the maximum context window?

The context window is 100,000 tokens for both prompt and completion combined. The maximum output per request is 16,000 tokens, or 2,048 tokens if the max_tokens parameter is not explicitly set.

What payment methods are accepted?

Crypto only: USDT (TRC20) or USDC (Base). Any whole amount from $20 to $500 is accepted. Bonus credit is added for larger top-ups.

Can I use the API for free?

Yes, new accounts receive $0.50 of trial credit valid for 7 days. The trial is one per person.

dolphinuncensoredai.com

Your key is one form away

Create an account, copy the key, change the base URL. That is the whole setup.

Try with trial credit Read the docs

Dolphin uncensored ai API guide

Try it in one request

What you get

OpenAI-Compatible

Large Context

Streaming Support

JSON Mode

Function Calling

Privacy First

How it works

Create Account

Top Up Credit

Send Request

What people build with it

Adult Content Generation

Security Research

Roleplay Applications

Code Completion

From signup to first token: your 3-step setup

Why developers still choose uncensored models over GPT-4

dolphin uncensored AI for roleplay, writing, and coding

Roleplay & NSFW Stories

Technical Writing

Coding Agents

Stop guessing: avoid common uncensored API pitfalls

Migrate your OpenAI client in three simple steps

The uncensored API buyer’s checklist

Questions and answers

Your key is one form away