The run's priciest five minutes - 4.1 times a typical window. Every model call is metered, so a run's spend can be read window by window against its own baseline. For five minutes, 33 model requests from 9 agents landed at once - 4.1 times the run's typical five-minute spend. The burst bought something: the checkup agent finished its job.

Where this happened.

Source events.

Detected mechanically by the cost_spike detector from 2 telemetry event(s):

  • 28c6c515-dbee-452c-954e-e711d1dd871c
  • ed36eebc-860e-4c68-b5fb-1661c36fdd36