All Systems Operational

Uptime over the past 90 days. View historical uptime.
Dedicated Inference Operational
90 days ago
99.99 % uptime
Today
Model APIs Operational
90 days ago
99.99 % uptime
Today
Training Operational
90 days ago
99.91 % uptime
Today
Model Management API Operational
90 days ago
99.98 % uptime
Today
Web Application Operational
90 days ago
99.99 % uptime
Today
Homepage and Docs Operational
90 days ago
100.0 % uptime
Today
Operational
Degraded Performance
Partial Outage
Major Outage
Maintenance
Major outage
Partial outage
No downtime recorded on this day.
No data exists for this day.
had a major outage.
had a partial outage.

No incidents or maintenance related to this downtime.

May 10, 2026

No incidents reported today.

May 9, 2026
Training cluster is down due to a provider failure
Resolved - The issue has been resolved.
May 9, 20:24 PDT
Monitoring - Monitoring the fix. Most nodes are back online, but not all.
May 9, 20:18 PDT
Identified - Root-caused and fix is underway. Inference is not affected.
May 9, 17:30 PDT
May 8, 2026
Intermittent failure in loading the webapp — inference is *not* affected
Resolved - The issue is resolved.
May 8, 17:22 PDT
Investigating - We are currently investigating this issue.
May 8, 16:40 PDT
May 7, 2026
Elevated errors for models in single region
Resolved - This incident has been resolved.
May 7, 08:37 PDT
Investigating - Elevated errors for models deployed in us-central-1
May 7, 07:50 PDT
May 6, 2026

No incidents reported.

May 5, 2026

No incidents reported.

May 4, 2026

No incidents reported.

May 3, 2026

No incidents reported.

May 2, 2026

No incidents reported.

May 1, 2026

No incidents reported.

Apr 30, 2026
Planned Maintenance on our Training Cluster. Inference will not be affected.
Completed - The scheduled maintenance has been completed.
Apr 30, 03:00 PDT
In progress - Scheduled maintenance is currently in progress. We will provide updates as necessary.
Apr 30, 00:00 PDT
Scheduled - We will be undergoing scheduled maintenance on our Training cluster.

All active training workloads will be stopped so that we can do maintenance on the cluster. Data in the training cache will be unaffected.
Apr 29, 08:17 PDT
Apr 29, 2026

No incidents reported.

Apr 28, 2026

No incidents reported.

Apr 27, 2026

No incidents reported.

Apr 26, 2026

No incidents reported.

← Incident History Powered by Atlassian Statuspage