A mid-size company runs several Foundry chatbot deployments shared across different departments. The finance team wants to see how many tokens each department's application consumes every month for internal chargeback billing, and to receive an alert if any department's monthly usage suddenly crosses a set threshold. Which Foundry capability addresses this need?

Usage and cost monitoring with configurable alerts on token consumption is correct because it tracks token consumption per deployment over time and supports configurable alerts, which is exactly what finance needs to allocate costs across departments for chargeback and to be notified when any department's usage suddenly spikes past an expected threshold. A stricter content safety filter applied to each department's deployment is incorrect because content safety filtering controls what categories of harmful content are blocked in generated text, and it has no connection to measuring or reporting on token consumption for billing purposes. A lower temperature setting applied across all departmental deployments is incorrect because temperature is a generation parameter affecting the variety of response wording, and adjusting it does not produce usage reports or trigger cost alerts. A fine-tuning job run separately for each department's use case is incorrect because fine-tuning is a training process used to adapt a model's behavior to a specific task, and it does not track ongoing token consumption or notify anyone about crossing a usage threshold. Since finance's stated goals are per-department consumption visibility for chargeback and threshold-based alerting, the capability built specifically to measure and alert on usage and cost is the one that satisfies both requirements.