Backend Configurations

To set the backend limit on total token consumption and the percentage that triggers an alert, configure the following keys:

• tokenConsumptionLimit The key that specifies the total tokens allowed for the AI service.

• tokenConsumptionTrigger The key that specifies the percentage of tokenConsumptionLimit. When consumption exceeds this percentage, a trigger value will be set to true in the API response.

Last updated: 1 year ago