At a zero balance, requests return 402 insufficient_quota until a top-up is made.
An optional per-key monthly spend cap limits a single key. Past the cap, that key also returns 402.
Keep a positive balance to avoid interruptions.
How billing works
Each call is billed at the model's list price for the tokens used and debited from the prepaid USD wallet when the response completes. There is no separate API invoice and no per-model subscription, because API usage shares the wallet and prices of the rest of AI HUB.
At a zero balance, requests return 402 insufficient_quota until a top-up is made.
An optional per-key monthly cap limits a single key. Past the cap, that key also returns 402 while the rest of the account keeps working.
The cap is a soft cap. It is checked before each call, so the request that crosses the cap still completes and total spend can settle slightly above it. If an exact limit matters, the cap should be set a little below the true ceiling.
