Uncensored API
The Abliterated API for Uncensored Model Access
Access a single, reliable uncensored model via a standard OpenAI-compatible API. No subscriptions, no content refusals, just direct token billing via crypto.
- OpenAI-compatible chat API
- $0.25/$1.00 per 1M tokens
- Crypto top-ups only
Try it in one request
curl https://api.abliterated.top/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.abliterated.top/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.abliterated.top/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);What you get
Direct API Access
Use the standard /v1/chat/completions endpoint with any OpenAI SDK. Supports streaming, function calling, and JSON mode without extra configuration.
Transparent Pricing
Pay only for actual token usage: $0.25 per 1M input tokens and $1.00 per 1M output tokens. Errors and refusals do not consume your credit.
No Subscription Friction
Top up with USDT (TRC20) or USDC (Base) for any whole amount between $10 and $500. Credit never expires and includes bonus tiers.
Uncensored Model
The model id 'uncensored' answers without content refusals for lawful adult use. It is an open-weight model, not GPT, Claude, or Llama.
Privacy Focused
Sign up with Google or email. Prompts are not used for training, and no phone number is required to get your API key.
High Capacity
Supports a 64,000 token context window with up to 16,000 tokens per output request. Ideal for long-form coding and research tasks.
How it works
Sign Up
Create an account with Google or email to receive your immediate API key.
Top Up
Add credit via USDT or USDC to start using the API without a subscription.
Integrate
Point your OpenAI-compatible client to api.abliterated.top/v1 and start sending requests.
What people build with it
Uncensored Coding
Use the uncensored coding llm capabilities for unrestricted code generation and debugging. It handles complex technical contexts without unnecessary conversational filler or refusals.
NSFW Content Generation
Generate adult content freely for lawful uses without hitting standard guardrails. The model is tuned to answer directly, making it ideal for creative writing.
Data Extraction
Leverage JSON mode to extract structured data from text reliably. The high context window allows processing large documents in single requests.
Research & Analysis
Run unrestricted analysis on controversial topics or security research data. The model provides direct answers without moralizing or filtering for political correctness.
What is Abliterated?
The term abliterated refers to models that have been explicitly tuned to remove the content refusals typical of major cloud providers. Unlike standard LLMs that might refuse lawful adult, political, or controversial topics, an uncensored llm like ours focuses on direct answers. We run a single open-weight model on our own servers, ensuring consistent behavior without the complexity of self-hosting.
This uncensored ai model is designed for developers who need reliability without the noise. It is not GPT, Claude, or any other vendor's model. It is a dedicated instance optimized for uncensored models that prioritize content availability over strict safety filtering for lawful use.
Direct API Access
Our API is fully OpenAI-compatible, meaning you can use your existing SDKs with minimal changes. Simply update the base_url to https://api.abliterated.top/v1 and provide your API key. We support streaming via SSE, function calling, and JSON mode, making it easy to integrate into your workflow.
curl https://api.abliterated.top/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
}'We do not offer embeddings, image generation, or audio processing. This is a pure text API. If you need those features, you will need a different provider. Our focus is on delivering a robust, high-context text model that developers can trust for consistent output.
Transparent Pricing
We charge $0.25 per 1M input tokens and $1.00 per 1M output tokens. There are no monthly subscriptions or hidden fees. You pay only for what you use, and errors do not consume your credit. Top-ups are done via crypto (USDT TRC20 or USDC Base) with amounts between $10 and $500. You also receive bonus credit for larger top-ups.
Every new account gets $0.50 in trial credit, valid for 7 days, with no card needed. This allows you to test the abliterated llm immediately. Your credit never expires, so you can use it at your own pace without worrying about subscription renewals.
Why Choose Us
We are an independent service, not a reseller of major vendor models. Our uncensored models are run on our own infrastructure, giving us direct control over performance and content behavior. We do not claim SLAs or certifications; we offer a straightforward, developer-first API.
This is NOT for users who need image generation, multi-model routing, or enterprise-grade SLAs. If you just want a reliable, uncensored text API with simple crypto billing, we are the right choice. We eliminate the friction of subscriptions and the complexity of self-hosting, letting you focus on your application.
Questions and answers
Is this a resell of GPT-4 or Claude?
No. We run our own open-weight model specifically tuned for uncensored responses. It is not GPT, Claude, Gemini, or any other vendor's model. You can verify this by checking the model id 'uncensored' in our API responses.
How do I top up my account?
We accept USDT (TRC20) and USDC (Base) only. You can top up any whole amount between $10 and $500. No credit cards or PayPal are accepted. Bonus credit is added for top-ups of $50 or more.
Does the model refuse content?
The model is uncensored and does not refuse lawful adult, fictional, or controversial topics. However, we do have a hard limit blocking sexual content involving minors. Everything else is generally allowed for lawful use.
What is the context window size?
The model supports a 64,000 token context window for both prompt and completion. You can request up to 16,000 tokens per output. If you do not set max_tokens, the default is 2,048 tokens.
Can I use the API with Python or Node.js?
Yes. Our API is OpenAI-compatible, so you can use the official OpenAI SDKs for Python, Node.js, and other languages. Just update the base_url to our endpoint and provide your API key.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
