Uncensored API

Dolphin ai models API Alternative

Migrate to a reliable uncensored LLM API with a 100,000 token context window and prepaid crypto billing for predictable costs.

Open account View documentation

Prepaid crypto billing only
100,000 token context window
No subscription lock-ins

Test with one call

curl https://api.dolphinaimodels.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Summit elevation is 29032 feet."}]
  }'

from openai import OpenAI

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

Features included

OpenAI Compatible

Drop-in replacement for existing clients using standard endpoints.

Uncensored Generation

Answers controversial topics without unnecessary refusals for adult content.

Streaming Support

Real-time token delivery via Server-Sent Events with usage stats.

Function Calling

Native tool support for dynamic response generation workflows.

JSON Mode

Enforce structured output using response_format for reliable parsing.

Crypto Payments

Top up with USDT or USDC without credit card fees.

Setup guide

Create Account

Top Up Credit

Add crypto funds to start using the uncensored endpoint.

Integrate API

Update base_url and call chat completions immediately.

Use cases

NSFW Chatbots

Run adult-themed roleplay without strict content filters.

Creative Writing

Generate edgy stories without unnecessary moralizing interruptions.

Data Extraction

Parse unstructured text with high token limits.

Research Analysis

Process large documents within the 100k context window.

Migrate from your current provider in three simple steps

Switch to our uncensored LLM endpoint by updating three configuration values. First, change the base URL to HTTPS://api.dolphinaimodels.com/v1. Second, replace your existing API key with the one generated from your account. Third, set the model ID to "uncensored" in your SDK settings. This works with any OpenAI-compatible client. You can now send requests without monthly fees or complex tiers.

from openai import OpenAI

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

dolphin AI models: Use cases for uncensored generation

The dolphin AI models API serves as a robust alternative for developers requiring unrestricted text generation without content filters.

NSFW Content Creation

Generate adult-oriented narratives without artificial refusals blocking lawful creative output.

Roleplay Integration

Deploy characters that respond freely to controversial topics or edgy dialogue scenarios.

Research & Analysis

Analyze data sets where standard models might sanitize sensitive but relevant information.

Raw Data Training

Extract unfiltered responses for fine-tuning your own specialized large language models.

How our infrastructure differs from typical alternatives

We run our own uncensored infrastructure for consistent context handling and predictable costs.

Feature	Typical Proxy	Ours
Context Handling	Variable routing	Consistent 100k tokens
Content Policy	Varies by vendor	Lawful adult uncensored
Billing	Monthly tiers	Prepaid tokens only
Model Source	Resold APIs	Our own servers
NSFW Workloads	Often blocked	Optimized for use
Cost Prediction	Unpredictable	Fixed token rates

Who should use this API and who should not

Developers needing a reliable, uncensored LLM endpoint for NSFW chatbots or unrestricted text generation should use this API. It handles high-volume workloads with predictable prepaid billing. Teams requiring image, audio, or embeddings should skip it. This service is not for those needing model routing or fine-tuning. It is ideal for anyone wanting to run the same client code as major providers but with lower costs and no monthly subscription lock-ins.

Calculate your costs: Token pricing examples

Pricing is $0.15 per million input tokens and $0.50 per million output tokens, charged only for real usage. Errors remain free. A 10,000-token request with 1,000 output tokens costs exactly $0.0065. No monthly fees or subscription lock-ins apply. Prepaid credits never expire. This transparent model ensures predictable expenses for high-volume uncensored generation without hidden tiers or surprise charges.

Access the uncensored LLM endpoint in minutes with zero configuration overhead.

Click Get API key and sign in via Google or email.
Receive your unique key instantly; no phone number required.
Top up $20+ using USDT or USDC to activate prepaid credit.
Update your SDK base URL to our API endpoint.
Send a POST request to receive text output immediately.

Common questions

What are dolphin AI models and how does your API differ?

They are uncensored LLMs fine-tuned for unrestricted output. Our service provides a hosted endpoint for the uncensored model, not the original vendor. You get predictable costs via prepaid tokens without monthly subscription fees or complex tier lock-ins.

Is the uncensored model completely free from refusals?

It handles controversial topics without standard content filters. However, a hard limit always applies: requests involving sexual content with minors are refused. All other lawful adult, fictional, or security-research topics are processed normally.

How much does it cost to use the API?

Input tokens cost $0.15 per million, and output tokens cost $0.50 per million. You pay only for real usage with prepaid credit. Errors and refusals do not consume your balance or tokens.

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.

What is the maximum context window size?

The model supports a 100,000 token context window for combined prompt and completion. Max output is 16,000 tokens per request, or 2,048 tokens if you do not specify max_tokens in your API call.

Is my prompt data used for training?

No. Prompts are not used for training. Your privacy is protected because we do not store or reuse your input data for model improvement. You only need an email address to create your account.

Unlock your API key

Open account