CASTAI Outage History

12 incidents recorded over the last 365 days, 12 of them resolved. Durations are measured from when PulsAPI first saw the problem to when it cleared, which is usually longer than the vendor's own figure.

Live CASTAI status100.00% uptime history

Every Recorded CASTAI Incident

CASTAI incidents, newest first, with date, duration and status.
DateIncidentDurationStatus
Oct 2, 2026Scheduled maintenance: Console login (US region) Maintenance has started1h 3mResolved
Oct 1, 2026Scheduled maintenance: Console login (EU region)Maintenance has started35 minResolved
Oct 1, 2026Scheduled maintenance: Console login (India region)Maintenance has started1h 0mResolved
Jun 16, 2026Degraded: CAST AI node provisioning issues on AKS with Kubernetes 1.36We have implemented a workaround and successfully remediated all affected clusters. Node provisioning is now functioning normally, and node functionality is not impacted. If you are running Kubernetes 1.36 and…3h 32mResolved
Jun 10, 2026Degraded Performance - api.cast.aiThe issue affecting the availability of api.cast.ai has been resolved.1h 15mResolved
Jun 4, 2026Intermittent Azure AKS Node Provisioning Failures in Select RegionsA fix has been deployed to restore compatibility with recent Azure AKS node bootstrap changes. We have not observed any additional affected customer clusters, and node provisioning is operating normally. If you…18h 25mResolved
May 27, 2026DocumentationCast AI documentation is now accessible. ReadMe reports their incident is resolved. https://www.readmestatus.com/26 minResolved
Apr 30, 2026Node Scaling Degradation for EKS Clusters in AWS UAE (me-central-1)At this time, we have not received any further updates from AWS regarding the earlier disruption in the UAE (me-central-1) region. Based on the current information available, we are closing this incident. We recommend…-86736 minResolved
Apr 30, 2026Degraded Performance – CAST AI Autoscaler**Update:** The issue affecting the CAST AI Autoscaler has been resolved. The autoscaler is now operating normally, and node provisioning has been fully restored.40 minResolved
Apr 24, 2026Microsoft Azure VM Provisioning Issues in East US RegionAutoscaler node provisioning for AKS clusters in East US is working as expected from a Cast AI perspective. We are declaring our impact as resolved but will continue actively monitoring the situation. Microsoft reports…5h 13mResolved
Feb 2, 2026Ongoing issue with Azure AKS ClustersSystem should be fully recovered and node additional is operational. Resolution confirmed.10h 38mResolved
Dec 5, 2025Cloudflare API Incident Impacting Cast AI Console**C**onsole is now operating normally and is stable28 minResolved

Hear about the next one while it is open

Everything above is a record written after the fact. We can email you when the next CASTAI incident opens instead, at the point where knowing still changes what you do.

Free, no password, no card. Unsubscribe in one click.

How to Read This CASTAI Incident Log

Each row is an incident PulsAPI observed, not a summary written afterwards. The duration is wall-clock time between the first failing check and the first clean one, so it includes the window before CASTAI acknowledged anything. Vendor post-mortems typically measure from acknowledgement, which is why their numbers are usually shorter.

Incidents still open have no duration yet and are listed as ongoing rather than being given a running total. The archive covers the last 365 days; anything older has aged out of the window rather than never having happened.

The longest single CASTAI outage in this window ran 18h 25m, against a mean recovery of 3h 56m. If you depend on CASTAI in a customer-facing path, the longest figure is the one to design around. The mean is what happens on a normal bad day; the maximum is what happens on the worst one.