Uncensored LLM API

Obliterated AI: The Uncensored LLM API

Get an uncensored model with a 100,000 token context window via standard OpenAI-compatible endpoints for unrestricted text generation.

$0.15 per 1M input tokens
Crypto top-ups only
No monthly subscriptions

Get API key View documentation

Execute a single request

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

from openai import OpenAI

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

Capabilities

OpenAI Compatible
Works with existing SDKs using our base URL and standard endpoints.
Uncensored Output
Answers adult and controversial topics without unnecessary refusals or filters.
Streaming Support
Receive token-by-token responses via Server-Sent Events for low latency.
Function Calling
Integrate tools and JSON mode directly into your application workflows.
No Training Data
Your prompts are not used to train future model iterations.
Simple Limits
300 requests per minute with no complex tiered usage restrictions.

Setup flow

Create Account
Sign up with Google or email to get an API key instantly.
Top Up Crypto
Add credit using USDT or USDC with no card required.
Send Requests
Point your client to our endpoint and start generating uncensored text.

Common use cases

NSFW Roleplay
Generate unrestricted adult narratives without content filters blocking your story.
Creative Writing
Produce raw, unfiltered creative content for novels or scripts freely.
Coding Assistants
Use the model for code generation without strict output restrictions.
Data Extraction
Parse large documents efficiently using the 100k token context window.

Start generating text in minutes by creating an account and grabbing your key. Sign up with Google or email on the dashboard. No phone number required. Your API key appears immediately for immediate use.

Sign up via Google or email.
Copy your key from the dashboard.
Send requests to the /v1/chat/completions endpoint. Use the uncensored model id for direct, unrestricted output.

Why we are different: 5 signs you have found the right uncensored API

We offer raw inference without monthly subscriptions or hidden filters.

Feature	Typical Alternatives	Obliterated AI
Pricing	High monthly fees or complex tiers	Pay-as-you-go: $0.15 per 1M input tokens, $0.50 per 1M output tokens
Content	Strict moderation	Uncensored for lawful adult use
Payments	Crypto (USDT, USDC), bank transfers	Crypto only (USDT/USDC)
Complexity	Vendor lock-in	Single model, no routing
Subscription	Monthly commitments	No monthly fee
Model Type	Proprietary black boxes	Open-weight uncensored model

Obliterated AI Use Cases: NSFW Generation, Roleplay, and Unrestricted Coding

The obliterated AI API delivers raw, unrestricted text generation for NSFW stories, immersive roleplay, and uncensored coding tasks without content filters.

NSFW Content Creation

Generate adult-oriented narratives without refusals for lawful use. The model handles explicit themes directly.

Immersive Roleplay

Run continuous character interactions with a 100,000 token context window. Maintain long-term memory without artificial constraints.

Unrestricted Coding

Get code output without moralizing or unnecessary explanations. The uncensored LLM follows instructions precisely for development workflows.

What Developers Actually Ask: Answers to your questions about our uncensored model

Our uncensored model ignores content filters for lawful adult use. It handles NSFW chatbot requests and roleplay without refusal. You get an OpenAI compatible API endpoint for unrestricted text generation. The context window is 100,000 tokens. Output limits are 16,000 tokens per request. Streaming via SSE includes token usage data. Function calling and JSON mode are supported. Pricing is $0.15 per 1M input tokens. There are no monthly subscriptions. Sign up with Google or email. Trial credit is $0.50 for 7 days.

Who This API Is For: Ideal for NSFW Apps and Roleplay; Not for Enterprise SLAs

Who This API Is For

This uncensored API serves developers building NSFW apps, roleplay bots, and unrestricted coding tools who want zero content filtering without enterprise overhead. You get an open-weight model via standard endpoints, not a curated enterprise suite.

Unrestricted creative and adult content generation.
High-volume, unmoderated chat workloads.
Simple billing without monthly commitments.

Who It Is Not For

It is not for enterprises needing 99.9% SLAs, HIPAA compliance, or multi-model routing. If you need guaranteed uptime or premium support, this raw inference API is not your solution.

Cost Examples: Exact Token Arithmetic for NSFW and Coding Workloads

Our API charges $0.15 per million input tokens and $0.50 per million output tokens. A single 40,000-token uncensored chat consumes 0.006 credits for input and up to 8 credits for a full 16,000-token response. There are no monthly subscriptions or hidden fees. Errors are free. Prepaid credit never expires, ensuring your budget tracks actual inference only.

Frequently asked questions

What is obliterated AI and how does it work?

It is an open-weight model serving via an OpenAI-compatible endpoint. You send text and receive raw, uncensored responses without content refusals for lawful adult use. The model runs on our servers, eliminating vendor lock-in.

Does the uncensored model support streaming responses?

Yes, it supports streaming via Server-Sent Events. You receive tokens incrementally, with token usage details included in the final chunk. This allows your application to display output progressively as the model generates text.

What is the cost per token for input and output?

Input tokens cost $0.15 per million, and output tokens cost $0.50 per million. You pay only for real usage, with errors and refusals being free. Credit never expires, and prepaid amounts are charged strictly by token volume.

Can I use my existing OpenAI SDK to connect?

Yes, the endpoint is fully OpenAI-compatible. You simply update the base URL and API key in your client configuration. It works with standard libraries, requiring no custom code or complex routing logic to integrate.

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 crypto payment methods are accepted for topping up?

We accept USDT on the TRC20 network or USDC on the Base network. Top-ups range from $20 to $500.

Secure your API key

Get API key

Obliterated AI: The Uncensored LLM API

Capabilities

OpenAI Compatible

Uncensored Output

Streaming Support

Function Calling

No Training Data

Simple Limits

Setup flow

Create Account

Top Up Crypto

Send Requests