Uncensored API
Abliterated model API
Get a dedicated abliterated model API with a 100,000-token context window, designed for developers who need raw, uncensored output without content refusals.
Test in one call
curl https://api.modelabliterated.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "what is the capital of france"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.modelabliterated.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.modelabliterated.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);- 100,000 token context window
- Pay only for tokens
- Crypto payments only
Core capabilities
OpenAI Compatible
Drop-in replacement using standard endpoints and SDKs with minimal code changes.
No Content Refusals
The model answers controversial or adult topics without standard safety filter interruptions.
Streaming Support
Receive real-time token updates via Server-Sent Events for low-latency applications.
JSON Mode
Force structured output with response_format settings for reliable data parsing.
Tool Calling
Define external functions and let the model decide when to execute them.
Zero Subscription
Prepaid credit never expires, so you pay strictly for what you consume.
Setup guide
Get Your Key
Sign up with Google or email to receive your API key instantly.
Add Crypto Credit
Top up with USDT or USDC to start making requests immediately.
Send Requests
Point your client to our base URL and start generating uncensored text.
Use cases
NSFW Content Generation
Create adult fiction or roleplay without the model refusing specific themes.
Raw Data Extraction
Parse complex text without the model adding unnecessary conversational filler or disclaimers.
Research & Analysis
Process sensitive topics or controversial data without standard content moderation filters.
Custom Roleplay
Run character-driven chats where the model stays in character without breaking.
Move from OpenAI in three steps
Switch your base URL and API key to deploy our uncensored LLM immediately.
- Update
base_urltohttps://api.modelabliterated.com/v1. - Swap your key for the one issued at signup.
- Send requests to
/v1/chat/completionsusing modeluncensored.
Your existing OpenAI SDK code works without changes. Stream responses or call tools directly. No retraining needed.
From signup to your first token
Start by signing up via Google or email, then receive your API key instantly without any card.
- Top up with USDT (TRC20) or USDC (Base) starting at $20.
- Point your OpenAI SDK to
https://api.modelabliterated.com/v1using your key. - Send requests to
/v1/chat/completionswith modeluncensoredand receive tokens.
Pay only $0.15 per 1M input and $0.50 per 1M output tokens.
Why the abliterated model fits your workflow
The abliterated model delivers an uncensored LLM that processes text without refusals, making it ideal for NSFW chatbot applications and creative writing.
Uncensored Content Generation
Create adult-themed narratives without unexpected blocks or safety filter interruptions during streaming.
Developer Testing
Validate prompt responses in unrestricted environments using the standard OpenAI-compatible SDK endpoints.
Cost-Efficient Scaling
Pay only for tokens with no monthly fees, ensuring your uncensored AI API budget stays predictable.
Who this API is for (and who should skip it)
Who this API is for (and who should skip it)
Use this uncensored LLM for NSFW chatbot roles or creative writing needing zero refusals. It handles controversial topics without fluff. Skip it if you need image generation, embeddings, or model routing. You are not getting GPT or Claude; we serve one abliterated model. Ideal for developers who want direct, unrestricted text output without subscription traps.
Calculate your exact token costs
Your bill reflects raw token usage, not subscription traps. Input costs $0.15 per million tokens while output runs $0.50 per million. A 10,000-token prompt paired with an 8,000-token response totals just $0.007. Errors and refusals incur zero charges. This transparent pricing ensures you pay strictly for the compute you actually consume without hidden fees.
Your checklist for uncensored providers
Verify true abliteration
Ensure the provider explicitly states that safety filters are removed, not just relaxed. Confirm the model id is a specific uncensored variant, not a routed generic model. Check that refusal behavior is surgically removed for lawful adult content. Ensure no extra fluff or moralizing prefixes appear in the response. Verify that the API returns raw text without hidden moderation layers. Confirm that errors are free and token usage is transparent. Check that the base URL is compatible with standard OpenAI SDKs for easy integration.
Common questions
What is an abliterated model?
An abliterated model is a large language model with its safety filters surgically removed. It answers without refusal. Our uncensored LLM handles adult topics freely. You pay only for tokens used, with no subscription traps.
Does the API support function calling?
Yes, the API supports function calling. You can use tools and tool_choice parameters. This allows structured interactions. You do not need embeddings or image generation features, which we do not offer.
Is the pricing transparent?
Yes, pricing is transparent. We charge $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors are free. Credit never expires. You pay only for real usage.
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.
Does the model refuse NSFW content?
Generally no, it is uncensored. The model answers lawful adult prompts without refusal. Only sexual content involving minors is always refused. You get direct answers without extra fluff.
What is the context window size?
The context window is 100,000 tokens. This includes both prompt and completion. You can generate up to 16,000 tokens per request. Streaming is supported via SSE.
Claim your API key
Sign up, grab the key, update the base URL. That’s it.
