RunPod Endpoint Monitoring

Real-time metrics and alerts for your serverless endpoints

View Alert History
Auto-refresh:

Active Alerts

Jobs in Queue

-

Jobs in Progress

-

Worker Utilization

-%

Jobs Failed (Period)

-

Total Jobs Run

-

Completed + Failed

Worker Status

Job Metrics

Historical Metrics

Alert Configuration

jobs_in_queue ComparisonOperator.GTE 1 Cooldown: 30min
workers_running ComparisonOperator.GTE 4 Cooldown: 60min
workers_running ComparisonOperator.EQ 0 Cooldown: 60min
jobs_failed ComparisonOperator.GTE 1 Cooldown: 30min