The run's priciest five minutes - 6.3 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, 23 model requests from 6 agents landed at once - 6.3 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):

  • a75824dd-e656-4418-a7f8-360b6580f50e
  • 3d94c64a-5477-416f-9d5f-3fb34c25ebe5