Zero Refusals
Our uncensored model answers without filtering lawful adult or controversial topics.
Uncensored LLM API
Obliterated models: The Uncensored LLM API
Get the uncensored LLM you need with a 100,000 token context window, paying only for what you use via crypto.
- 100,000 token context window
- Crypto only, no subscriptions
- OpenAI compatible endpoints
Test with a single request
curl https://api.obliteratedmodels.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "List all active ports on the server"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.obliteratedmodels.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.obliteratedmodels.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
Core capabilities
OpenAI Compatible
Use standard SDKs with our base URL and API key instantly.
Streaming Support
Receive token-by-token responses via SSE with usage in the final chunk.
JSON Mode
Force structured output with response_format json_object for reliable parsing.
Tool Calling
Execute function calls with tools and tool_choice parameters.
No Training
Your prompts stay private and are never used for model training.
Setup process
Get Key
Sign up with Google or email to receive your API key.
Add Credit
Top up with USDT or USDC to start making requests.
Send Request
Call POST /v1/chat/completions with your model id uncensored.
Common use cases
Roleplay
Generate unrestricted character dialogues without content filter interruptions.
Data Parsing
Extract structured JSON from complex text inputs reliably.
Creative Writing
Produce long-form stories with a 100k token context window.
Research
Analyze large documents without bias from standard safety layers.
Why We Are Different: 4 Concrete Signs
We eliminate subscription fluff by offering pure pay-per-token billing. Our uncensored model runs on dedicated servers, not shared infrastructure. You pay $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors cost nothing. This transparency ensures you never overpay for idle capacity.
| Feature | Us | Typical |
|---|---|---|
| Billing | Pay-per-token | Subscription |
| Content | Uncensored | Filtered |
Real Cost Examples: Token Arithmetic
Calculating expenses is straightforward with our prepaid model. A 100K token prompt costs $0.015, while a 16K output runs $0.008. Streaming reveals usage in the final chunk, ensuring you pay only for consumed tokens. Errors remain free. This transparency eliminates hidden fees, allowing precise budgeting for high-volume NSFW chatbot deployments without monthly subscriptions.
obliterated models: Use Cases & Applications
Persona Development
Deploy uncensored characters without refusal interruptions. The model handles nuanced, adult-oriented dialogues reliably.
Content Generation
Create unrestricted NSFW stories or scripts. No hidden filters block creative freedom for lawful uses.
Research Testing
Bypass standard guardrails to evaluate model behavior under diverse, controversial prompts efficiently.
How It Works: From Signup to First Token
Get your API key in seconds, top up with crypto, and start generating.
- Sign up using Google or an email address—no phone number required.
- Add credit via USDT (TRC20) or USDC (Base). Any amount between $20 and $500 works.
- Configure your client by setting the base URL to
https://api.obliteratedmodels.com/v1and pasting your key. - Send requests to
POST /v1/chat/completionswith the model IDuncensored.
Common Mistakes in the Uncensored Niche
Developers often assume uncensored models handle all tasks flawlessly, leading to unexpected refusals or hallucinations. Many confuse context window limits with output limits, causing truncated responses when generating long texts. Others neglect to set max_tokens, wasting credits on infinite streaming. We guarantee no hidden fees, but you must manage your own token counts. Our API returns raw text without built-in moderation, so you handle the logic. Configure your client correctly to avoid these common pitfalls.
Who It Is For: And Who It Isn't
Developers needing an uncensored LLM for NSFW chatbot or unrestricted AI tasks should use this API. It handles complex prompts without refusal, ideal for roleplay or security research.
- Best for: Power users wanting transparent crypto billing and 100k context windows.
- Worst for: Teams requiring embeddings, image generation, or monthly subscription models.
If you need a simple, cheap LLM API without marketing fluff, this is your solution. Stop paying for unused features.
Frequently asked questions
What is the abliterated models API and how does it work?
It is an uncensored LLM service. You send prompts via OpenAI-compatible endpoints. Input text generates output without content refusals. We charge $0.15 per million input tokens. Errors are free.
Is there a monthly subscription fee?
No. We use a prepaid crypto model. You top up with USDT or USDC. Credit never expires. You pay only for actual token usage. No monthly fees apply.
Can I use the standard OpenAI SDK?
Yes. The API is fully compatible. Change the base URL to our endpoint. Use your API key. Send requests to /v1/chat/completions. Streaming and JSON mode work.
How fast is the uncensored model?
It supports 300 requests per minute. You can run eight concurrent requests. Context windows hold 100,000 tokens. Output limits reach 16,000 tokens. Throughput is high.
What crypto payment methods are accepted?
We accept USDT on TRC20 or USDC on Base. Top-ups range from $20 to $500. Bonuses apply for larger amounts.
Is my data used for training?
No. Prompts are not used for training. We only require an email. Your data stays private. Requests are processed directly. No third-party sharing occurs.
Secure your API key
Register, copy the key, and update the endpoint URL. That is the entire configuration.
