HomeGet API key
Get Your LLM API Key
Generate your AI API key in seconds by signing up with just an email and password. You receive immediate access to an uncensored LLM API with a free trial credit, requiring no credit card or phone verification.
Your API key
Keep this key secret. Anyone who has it can spend your credit.
Base URL:
Model:
Balance: $
Requests:
Crypto top-ups (USDT, USDC) are available on this site. Until then your trial credit applies.
- per 1M input tokens
- $0.25
- Output tokens / 1M
- $1.00
- token context
- 100,000
- trial credit
- $0.50
- requests per minute
- 300
What you get
Instant Key Generation
Your API key appears immediately upon signup, ready to paste into your existing OpenAI-compatible clients.
No Card Required
Start with $0.50 of trial credit without linking a payment method or providing a phone number.
Transparent Pricing
Pay-as-you-go prepaid credit with no monthly subscriptions, ensuring you only pay for the tokens you use.
Dedicated Infrastructure
Access a single, high-capacity uncensored model optimized for unrestricted generation without multi-model routing overhead.
How it works
Create Account
Enter your email and choose a password to register on the Get API key page.
Receive Your Key
View your unique AI API key instantly on the screen, which is valid immediately.
Connect Your Client
Paste the key and the base URL into your code to start sending requests to the LLM API.
What You Get with Your Key
Your new key provides immediate access to a hosted, OpenAI-compatible chat-completions API. You can send text requests to the endpoint POST /v1/chat/completions and receive responses in JSON format, with support for streaming via Server-Sent Events (SSE) and tool/function calling. The API serves a single, dedicated uncensored large language model hosted on our own GPU servers. This model is optimized for unrestricted generation, meaning it answers controversial, adult, or security-research topics without the typical refusals found in other models. It is an open-weight model, not a rebranded GPT or Claude instance. You will have access to a 100,000-token context window, allowing for substantial input and output per request. All requests are limited to a maximum body size of 8 MB, and you can send up to 300 requests per minute. The API supports standard OpenAI SDKs, so you only need to change the base URL and API key in your existing code to get started.
Billing and Trial Details
Every new account receives $0.50 in trial credit, which is valid for 7 days. This trial requires no credit card and no phone number, allowing you to test the API thoroughly before committing funds. When your trial credit expires or runs out, you can top up with prepaid credit starting at $10. We offer a +5% bonus on deposits of $50 and a +10% bonus on deposits of $100. There are no monthly subscriptions or hidden fees; you pay only for the tokens you consume. Pricing is set at $0.25 per 1 million input tokens and $1.00 per 1 million output tokens. Your prepaid credit never expires, so you can use it whenever you need to run your models. You can manage your balance and regenerate your API key at any time from your account dashboard if needed.
Questions and answers
Is a credit card required to sign up?
No, you do not need a credit card or phone number to create an account. You can sign up with just an email and password to receive your $0.50 trial credit. You only need to provide payment details when you choose to top up your balance with prepaid credits.
What happens when my trial credit ends?
Your trial credit is valid for 7 days from signup. Once it expires or is exhausted, you will need to add prepaid credits to continue using the API. You can top up starting at $10 via crypto (USDT or USDC), and you will receive bonus credits on larger deposits.
How do I replace a leaked or compromised key?
You can regenerate your API key at any time from your account settings. When you generate a new key, the old one is immediately revoked, ensuring that anyone who had the previous key can no longer use it. Each account is limited to one active key at a time.
Is this API suitable for production use?
Yes, the API is designed for production workloads with a 300 requests per minute limit per key and an 8 MB request body limit. It supports standard OpenAI-compatible protocols, making it easy to integrate into existing systems. However, it does not offer SLA guarantees or multi-model routing, so it is best suited for applications that require a specific, uncensored model rather than dynamic routing between vendors.
