Pricing

Token Pricing

We charge strictly by token usage. Input tokens cost $0.15 per million, and output tokens cost $0.50 per million. This transparent billing means you never pay for idle time or subscription tiers. You only pay for the tokens your model processes. Errors and refusals are free. This model is not GPT, Claude, or Grok. It is an open-weight model tuned for law-abiding adult use. We do not use your prompts for training. Your data stays yours. The pricing is simple and predictable. You can track your exact spend in real-time. There are no hidden fees or surprise charges. This is a direct, utilitarian approach to LLM inference. We strip away the marketing fluff. You get raw, uncensored access. The cost is exactly what you see. No more, no less. This is the most unhinged AI pricing you will find.

Prepaid Credit & Crypto Payments

Top up your balance with USDT (TRC20) or USDC (Base). We accept whole amounts from $20 to $500. Your credit never expires. Sign up with Google or email. Your API key appears immediately. No phone number is needed. The trial gives you $0.50 for 7 days. Prepaid credit keeps your spend predictable. You control your budget precisely. Refunds are not issued, but mistakes are fixed via Support. Your credit is yours until you use it. We offer a simple, direct payment method. Crypto is the future. We embrace it fully. No middlemen. No delays. Just fast, reliable topping up. Your unhinged chatbot runs smoothly.

Bonus Credit Tiers

Get extra credit when you top up. Add $50 for a 5% bonus. Add $100 for a 10% bonus. Add $200 for a 15% bonus. This extra credit lowers your effective cost per token. It rewards your commitment. The bonus applies immediately. You can use it for any request. There are no expiration dates on bonus credit. It expires with your main balance. This is a great way to save money. We want you to succeed. Your projects need reliable inference. We provide the tools. The bonuses are automatic. You do not need to do anything. Just top up and start using. The uncensored AI model is ready. Your content is safe. We do not moderate heavily. You get what you need. This is the best uncensored image generation API? No, we do text. But we do it well. With bonuses, it is even better.

Limits and Fair Use

You get 300 requests per minute per key. You can run 8 requests simultaneously. The request body limit is 8 MB. One active key per account. A new key replaces the old one. These limits prevent abuse. They ensure fair use for everyone. The uncensored model handles high throughput. It is built for production. You can stream responses via SSE. Function calling is supported. JSON mode is available. Temperature, top_p, and stop parameters work as expected. The context window is 100,000 tokens. Max output is 16,000 tokens. The trial lasts 7 days. This is a cheap LLM API. We keep it simple. No complex tiers. No hidden limits. Just raw power. Your unhinged AI model waits. It is ready to serve. We do not overpromise. We deliver exactly what we say. This is the most unhinged AI experience.