OpenAI Compatible
Drop into existing clients by updating the base URL and API key.
Uncensored LLM API
Abliter: The Uncensored LLM API
Get direct access to our single uncensored LLM model via an OpenAI compatible API, handling 100,000 token context windows for reliable NSFW content generation without extra fees.
- 100k token context window
- Crypto top-ups with bonuses
- No monthly subscription fees
Test with one call
curl https://api.abliter.cc/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "What is the current server status?"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.abliter.cc/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.abliter.cc/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);- $0.15per 1M input tokens
- $0.50Output tokens / 1M
- 100,000token context
- $0.50trial credit
- 300requests per minute
What’s included
Uncensored Model
Answers without refusals for lawful adult, fictional, or controversial topics.
Streaming Support
Receive tokens via SSE with usage data in the final chunk.
Function Calling
Use tools, tool_choice, and JSON mode for structured responses.
Transparent Pricing
Pay $0.15 per million input tokens and $0.50 per output tokens.
Crypto Payments
Top up with USDT or USDC and receive bonus credit.
Setup guide
Create Account
Sign in with Google or email to get your key instantly.
Add Credit
Deposit crypto to activate your account and start sending requests.
Send Request
Post to the chat completions endpoint with your model id.
Use cases
Character Roleplay
Generate uncensored dialogue for interactive stories without content filters blocking you.
Data Extraction
Parse large documents using the 100k context window for deep analysis.
API Integration
Replace existing LLM providers in your app with one simple config change.
Research Testing
Test model outputs on controversial topics without standard safety refusals.
Get the abliter API Key in Seconds
Start testing with $0.50 trial credit valid for seven days.Instant Access
Sign up via Google or email to receive your active key instantly. No subscriptions, no monthly fees, just pay per token.
Crypto Top-ups
Add funds using USDT (TRC20) or USDC (Base). Amounts range from $20 to $500 with bonus credits for larger deposits.
Transparent Pricing
Pay $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors are free, and prepaid credit never expires.
Who Uses Our Uncensored LLM API and Who Should Skip It
Developers building NSFW chatbots or unrestricted creative writing apps use our API. The uncensored model handles adult themes without refusals. Skip us if you need embeddings, image generation, or multiple model routing. We serve text only via one specific server. Character AI users seeking direct access prefer this path. You must accept crypto top-ups. This is a raw API for builders who want total freedom and transparent token pricing without subscription fees.
From Signup to First Token in 4 Steps
From Signup to First Token in 4 Steps
- Visit the Get API key page and sign up via Google or email.
- Your unique API key appears instantly; no phone number is required.
- Copy the key and paste it into your OpenAI-compatible SDK client.
- Point the base URL to
https://api.abliter.cc/v1and send your first message to theuncensoredmodel.
Common uncensored API Mistakes
Developers often confuse proxy services with dedicated infrastructure, leading to unexpected latency and hidden model routing. We run our own server-tuned model, so you get direct access without third-party intermediaries. Another frequent error is ignoring the 100,000-token context window, which causes premature truncation during long conversations. Always set max_tokens to 16,000 to ensure full responses. Finally, do not assume unlimited concurrency; our limit is eight simultaneous requests per key. Use streaming to manage load effectively.
How Abliter Differs from Generic Proxies
Abliter connects directly to one uncensored LLM, avoiding proxy markup and multi-model routing delays. You pay $0.15 per 1M input and $0.50 per 1M output tokens, with prepaid credit topping up via USDT or USDC only. Errors are free. This single-server model ensures consistent latency and complete freedom for lawful adult content without hidden subscription fees.
Compute Your Exact Spend
Costs depend strictly on token volume. Input runs $0.15 per million tokens; output costs $0.50 per million tokens. A 5,000-token prompt plus 500-token response totals $0.0035. Errors incur zero charges. Streaming returns usage data in the final chunk. Prepaid credits never expire. You only pay for what you actually consume.
Common questions
What is abliter and how does it work?
It is an uncensored LLM API. You send text, receive text. Use the standard OpenAI-compatible endpoint. No routing, just direct access to our single model.
Does the model refuse adult content?
No. It does not refuse lawful adult content. Exceptions include minors. Everything else remains open. You get full freedom for creative or unrestricted projects.
How much does it cost to use the API?
$0.15 per million input tokens. $0.50 per million output tokens. Errors cost nothing. Pay only for actual usage. Credit never expires. No monthly fees.
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.
What is the maximum context window?
It supports 100,000 tokens total. This includes both prompt and completion. You can generate up to 16,000 tokens per request. Longer outputs are possible.
Does the API support function calling?
Yes. You can use tools and tool_choice. JSON mode is also available. Streaming works via SSE. All standard parameters like temperature and seed are supported.
