For the complete documentation index, see llms.txt. This page is also available as Markdown.

Backend Configurations

To set the backend limit on total token consumption and the percentage at which to send a trigger, configure these keys:

  • tokenConsumptionLimit

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

  • tokenConsumptionTrigger

    • The key that sets a percentage of the value in tokenConsumptionLimit. When that percentage is exceeded, a trigger value will be set to true in the API response.