What does this combine?

Chat LLM + embedding model + vector DB + cache + compute (Vercel/Cloudflare workers) + storage = total true infra bill for a RAG-based AI app.

💸

AI Stack Real Cost Total

Models + Embeddings + Vector DB + Compute

Daily user queries

Avg input tokens

Avg output tokens

Chat model

Cache hit rate

Embedding queries / day

Vector DB

Compute

📚

Learn more — how it works, FAQ & guide

Click to expand

Calculate exact age in years, months, days, hours

Body Mass Index — metric and imperial

Calculate tips and split bills between people

🔒

100% Privacy. This tool runs entirely in your browser. Your data is never uploaded to any server.