Raw LLM API

Obliterated model: Uncensored API for Developers

Get an uncensored LLM via our openai compatible API with a 100,000-token context window and crypto-only payments.

$0.15 per 1M input tokens
100,000 token context window
No monthly subscriptions

Test with one call

curl https://api.obliteratedmodel.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the top 5 linux commands for disk usage."}]
  }'

from openai import OpenAI

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

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

Features

OpenAI-Compatible

Works with standard SDKs by changing just the base URL.

Uncensored Output

No refusals for lawful adult content or controversial topics.

Streaming Support

Get token usage in the last chunk via SSE streams.

Function Calling

Use tools and tool_choice for structured data extraction.

JSON Mode

Force strict JSON output with the response_format parameter.

Crypto Top-ups

Top up with USDT or USDC for bonus credits.

Getting started

Create Account

Add Crypto

Top up with USDT or USDC for bonus credits.

Send Request

Point your SDK to our base URL and start coding.

Use cases

Uncensored Coding

Generate code without guardrails blocking technical or mature topics.

NSFW Chat

Deploy chatbots that answer adult questions without refusal.

Research Models

Test open-weight models without third-party content filters.

Unhinged AI

Build agents that respond freely to any prompt input.

Why the obliterated model changes how you build

Use the uncensored LLM for content that standard APIs reject. We serve one raw model without guardrails or extra fluff.

Uncensored Coding AI

Generate code that ignores safety filters for proprietary logic or edge cases.

Unfiltered Chatbot

Build chat interfaces that answer controversial topics directly without polite refusals.

NSFW Model

Process adult content freely as long as it does not involve minors.

Unhinged AI

Get creative, unvarnished text generation without corporate tone adjustments.

Switching from OpenAI in three simple steps

Move your workload to the uncensored LLM by updating three configuration fields. First, set your base URL to HTTPS://api.obliteratedmodel.com/v1. Second, paste your new API key into the authorization header. Third, change the model ID to "uncensored". This openai compatible API accepts standard payloads, so your existing SDK logic remains intact. You get unrestricted responses immediately without rewriting your application code.

H2: Four signs this is the uncensored LLM you need

This uncensored LLM serves a single, unfiltered open-weight model via a strict OpenAI-compatible endpoint, eliminating proxy wrappers. Unlike generic alternatives, we provide a transparent prepaid credit system with crypto-only top-ups, no monthly subscriptions, and no data training on your prompts.

Feature	Us
Model Selection	One optimized uncensored model
Pricing	Pay per token, no subscription
Payments	Crypto only (USDT/USDC)
Privacy	Prompts not used for training
Refusals	None for lawful adult content

What developers actually ask about abliterated models

Uncensored models remove refusal guardrails to allow direct answers for adult, fiction, or controversial topics. The primary trade-off is that removing these constraints often impacts general quality and faithfulness to the base model. Our service runs a single open-weight model on our own servers, ensuring no data training on your prompts. You get a strict OpenAI-compatible endpoint with a 100,000-token context window and crypto-only top-ups starting at $20.

Who benefits from this uncensored LLM and who should skip

Developers needing raw, unfiltered outputs use this uncensored LLM for creative writing or testing content boundaries. It suits those avoiding corporate guardrails. Skip if you require image generation, embeddings, or fine-tuning. It is not for teams needing complex model routing or strict data residency. Use it when you want direct, open-weight responses without extra fees or subscription locks.

How to get your first answer in 5 minutes

Get an uncensored LLM response by creating an account and adding prepaid credit.

Sign up with Google or email to receive your API key immediately.
Add credit via USDT or USDC, starting at just $20.
Configure your SDK by pointing to our OpenAI-compatible base URL.
Send a request to the uncensored model endpoint.

Start generating text without complex routing or monthly subscriptions.

FAQ

What is the obliterated model API?

It is an uncensored LLM API compatible with OpenAI. It uses the standard chat-completions endpoint. You send text and get text back. The model does not refuse lawful adult content. It runs on dedicated servers. You pay per token. Credits never expire. No subscriptions required.

Does it support function calling?

Yes, it supports function calling. You can define tools and use tool_choice. The API handles tool execution. It also supports JSON mode. Streaming via SSE is available. Token usage appears in the last chunk. This allows flexible integration into your apps.

How much does it cost?

It costs $0.15 per million input tokens. Output tokens cost $0.50 per million. Errors and refusals are free. You pay only for real usage. Top-ups are crypto only. Credits never expire. You can add bonus credit. No monthly fees exist.

Is data used for training?

No, prompts are not used for training. Your data stays private. We do not use your inputs. This ensures confidentiality. You can use it for sensitive projects. The model answers without filtering. Your context remains yours.

What is the context window?

The context window is 100,000 tokens. This includes prompt and completion. Max output is 16,000 tokens. Set max_tokens to avoid limits. Default is 2,048 tokens. This handles long documents. Streaming works smoothly. Configure parameters freely.

Can I use any SDK?

Yes, use any OpenAI-compatible client. Change the base URL. Set your API key. The endpoint matches the standard. Streaming and JSON work. Tools function correctly. It integrates easily. Code adapts quickly.

Get your API key

Get API key