The run's priciest five minutes - 2.1 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, 91 model requests from 8 agents landed at once - 2.1 times the run's typical five-minute spend. The burst bought something: the code agent finished its job.

Where this happened.

Source events.

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

  • 6684ff05-555a-4389-94c6-050c9ba942e9
  • bd8e125f-1af0-4364-9bdb-1986a1533123