The quota fallback question also has a concurrency side. If several editor requests begin just below the monthly limit, each can independently appear eligible and collectively exceed it before their token usage is recorded.
I would reserve an estimated allowance when a request starts, reconcile it against reported usage, and show the selected provider before the editor accepts the result. That makes the local fallback visible at the point where output quality can change, while giving administrators a budget whose behavior stays understandable under a busy publishing session.
Agreed, a check-then-record quota lets every request that starts just under the limit through, and the overshoot only shows once usage is logged. Reserving an estimate up front and reconciling it afterwards closes most of that gap, and showing the selected provider before the editor accepts the output is exactly where the fallback should be visible.
Ahmet Özel
The quota fallback question also has a concurrency side. If several editor requests begin just below the monthly limit, each can independently appear eligible and collectively exceed it before their token usage is recorded.
I would reserve an estimated allowance when a request starts, reconcile it against reported usage, and show the selected provider before the editor accepts the result. That makes the local fallback visible at the point where output quality can change, while giving administrators a budget whose behavior stays understandable under a busy publishing session.