Zolani Matebese

Not all of them. Anthropic reports ordinary input, cache creation and cache reads in separate usage fields. Culpa preserves these separate buckets before pricing them, so the cost attached to your conversation, feature and customer doesn t quietly leave cached usage out.

Anthropic s pricing documentation tells you to calculate total input by adding input_tokens, cache_creation_input_tokens and cache_read_input_tokens. It also prices ordinary input, cache writes and cache reads differently.

not so fast though; that creates an easy spreadsheet mistake. If you take input_tokens and treat it as the whole request, you'll see that cached context can disappear from your calculation even though Anthropic still reports and prices that usage separately.

Retries can move your AI bill even when customer activity, completed workflows and model choice stay almost unchanged. Culpa keeps repeated calls attached to the workflow and conversation that caused them, so you can see when you re paying several times for one piece of customer work.

The economics are simple. A retry doesn t erase the first attempt. If two attempts fail and the third succeeds, your customer receives one result while you may have paid for three model calls.

That is why total calls per day isn t enough. You need to compare model calls with the amount of customer work completed.

A sudden AI bill increase usually comes from a fairly small number of places: you made more calls, each call became more expensive, or your application started doing work you didn t realise was happening.

The problem is that the total bill doesn t tell you which one.

• So how to find out?