Zero Content Filters
Our open-weight model answers controversial, NSFW, and roleplay topics without unnecessary refusals. It is not GPT or Claude; it is built specifically for unfiltered output.
Uncensored LLM API
The Abliterated LLM API for Unfiltered Content
A single, purpose-built uncensored model with zero refusals for lawful adult content. Stop managing multiple models and start building.
- One uncensored model
- $0.25 input / $1.00 output
- 64k context window
Try it in one request
curl https://api.abliteratedapi.com/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.abliteratedapi.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.abliteratedapi.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);- $0.25per 1M input tokens
- $1.00Output tokens / 1M
- 64,000token context
- $0.50trial credit
- 300requests per minute
What you get
OpenAI Compatible
Drop-in replacement for existing integrations. Uses the standard chat-completions endpoint with streaming and tool support.
Transparent Pricing
Pay-as-you-go with no subscriptions. Input tokens are $0.25 per million; output tokens are $1.00 per million. Credits never expire.
Large Context Window
Process up to 64,000 tokens per request. Ideal for long-form roleplay, document analysis, and complex prompt chains.
Instant Access
No phone number or credit card required for the trial. Get your API key immediately after signing up with email and password.
Private & Secure
Prompts are not used for training. You control your key and can regenerate it instantly if needed.
How it works
- 1
Sign Up
Create an account with just an email and password.
- 2
Get Your Key
Receive your API key instantly and receive trial credit.
- 3
Start Building
Point your SDK to our base URL and make your first request.
What people build with it
NSFW Roleplay
Build character-driven chat applications that handle adult themes naturally. No more unexpected blocks when the story gets spicy.
Content Creation
Generate unfiltered marketing copy, stories, or scripts without corporate safety filters interfering with your creative voice.
Security Research
Test model jailbreaks and prompt injection attacks in a controlled environment. Get raw outputs without moderation layer interference.
Data Annotation
Use the model to label or categorize text without bias from standard safety fine-tuning affecting your results.
Why Abliterated?
Most API providers offer a collection of models, but that complexity often comes with hidden content filters. We chose a different path: one high-quality uncensored model, optimized for reliability. When you search for an uncensored llm api, you want consistency, not a lottery of different refusal rates across different models. Our model is tuned to answer, not to judge. It handles adult, controversial, and niche topics with equal ease. This approach reduces integration complexity because you only need to support one model architecture. You get predictable behavior across your entire application, whether you are building a chatbot for adults or a research tool for open-ended generation.
One Model, Zero Filters
Our model is an open-weight solution hosted on our own GPU servers. It is not GPT, Claude, Gemini, or DeepSeek. It is purpose-built to minimize refusals for lawful adult content. While we maintain a hard limit against sexual content involving minors, everything else is fair game. This includes explicit language, sexual themes, and controversial opinions. Unlike commercial APIs that may rotate models or update safety layers without notice, our model remains stable. You know exactly what you are getting. This stability is crucial for developers who have built their application logic around specific model behaviors. You do not need to write fallback logic for different models. You just send text in and get text out.
OpenAI Compatible
We use the standard OpenAI-compatible endpoint structure. This means you can use the official OpenAI SDKs for Python, Node.js, and other languages. Simply update your base URL to https://api.abliteratedapi.com/v1 and provide your API key. The endpoint POST /v1/chat/completions supports streaming via Server-Sent Events (SSE) and tool/function calling. We do not offer embeddings, image generation, audio, or video. We focus entirely on text completion. This simplicity reduces overhead and keeps our pricing transparent. You can test your integration immediately using the trial credit provided with every new account. No credit card is required to start.
Transparent Pricing
Our pricing is straightforward and based on actual usage. There are no monthly subscriptions or hidden tiers. Input tokens cost $0.25 per million tokens, and output tokens cost $1.00 per million tokens. You preload credit, and it never expires. If you top up $50, you receive a 5% bonus. Top up $100 and get a 10% bonus. This model ensures you only pay for what you use. We also offer a generous context window of 64,000 tokens for both prompt and completion. This allows you to process long documents or maintain extensive conversation history without excessive costs. We do not charge per request, so burst traffic does not penalize you. This is ideal for projects with variable usage patterns.
Questions and answers
Is this API really uncensored?
Yes. Our model is tuned to answer without refusing common adult, controversial, or explicit topics. It is not GPT or Claude. The only hard limit is sexual content involving minors, which is always blocked. Everything else is allowed for lawful use.
What is the context window size?
Our API supports a 64,000 token context window. This includes both the input prompt and the output completion. This allows for long-form generation and complex multi-turn conversations without losing context.
Do I need a credit card to start?
No. You can sign up with just an email and password. Every new account receives $0.50 in trial credit valid for 7 days. No card is required to test the API.
What models do you offer?
We offer one model: "uncensored". It is an open-weight model hosted on our servers. We do not route between different vendors or offer model selection. This ensures consistent behavior and predictable pricing.
Who is this NOT for?
If you need embeddings, image generation, audio, or video, this is not for you. We also do not offer fine-tuning or SLA guarantees. If you require HIPAA compliance or SOC2 certification, you should look elsewhere. This is for developers who need simple, unfiltered text generation.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
Get API key