Token Desk

Read a prompt written one part at a time and see what the whole thing costs. A conversation bills the SQUARE of its own turn count, because every turn re-sends the whole history: a 2,000-token prompt over 30 turns bills 327,000 input tokens while the final context - the thing you can see - is only 20,000, and a budget built from the per-call price times the turn count understates it by 2.35x. A few-shot example is a per-call cost, not a one-off: eight at 250 tokens is 2,000 on every single call, $21,900 a year at 10,000 calls a day. The window holds input AND output, so a 200k window with a 64k maximum output leaves 136,000 for input - 224 turns fit where the model card promised 330. A cache breakpoint covers a PREFIX, so a 40-token timestamp at the top of a 2,000-token prompt makes all of it uncacheable while the same line at the bottom leaves 98% cached, and nothing reports it. And at or below one call per TTL, caching costs exactly 25% MORE than not caching. Five lanes over one prompt budget sheet: plan a prompt the window and the budget can pay for, read what an existing one costs per call and per conversation, price the turns and the cache, and decide what to change. Free browser-side arithmetic - no model is called and this page does not tokenise.

Every public app is built from a security-scanned skill and must pass a clean scan — skill and frontend — before it can be listed. Have a skill of your own? Turn it into an app — or read the step-by-step walkthrough.