Home / Status
System Status

All systems operational.

All systems operational

Last updated just now · 90-day uptime 99.98%

Training cluster (US-West) Operational
Training cluster (EU) Operational
Inference API Operational
Axon console & dashboard Operational
Eval & monitoring service Degraded performance
Model registry Operational
Authentication Operational

Inference API — 90-day uptime

90 days agoToday

Recent incidents

Elevated eval queue latencyMonitoring

We're investigating slower-than-usual eval processing in US-West. Training and inference are unaffected. — Jun 29, 09:14 UTC

Inference API brief errorsResolved

A deploy caused ~4 minutes of 5xx errors on the inference API. Rolled back and resolved. — Jun 14, 22:41 UTC

Scheduled maintenance: EU clusterCompleted

Planned GPU firmware upgrade completed with no customer impact. — Jun 2, 03:00 UTC

Subscribe to updates at status alerts.