Update - We continue to investigate the issue and have narrowed down the root cause. Our team is actively working towards a resolution and will provide a further update as soon as possible.
Jul 08, 2026 - 11:03 UTC
Investigating - We are investigating an issue affecting the Crusoe Container Registry (CCR) in the US South Central (us-southcentral1-a) region. Beginning at approximately 04:07 UTC on July 8, 2026, customers may be unable to push or pull container images, and may see TLS handshake timeouts or authentication errors. Our engineering team is actively investigating. We will provide more information as we investigate the issue.
Jul 08, 2026 - 05:23 UTC
GPU Virtual Machines
Operational
90 days ago
99.93
% uptime
Today
us-east1
Operational
90 days ago
99.75
% uptime
Today
us-northcentral1
Operational
90 days ago
100.0
% uptime
Today
us-southcentral1
Operational
90 days ago
100.0
% uptime
Today
eu-iceland1
Operational
90 days ago
100.0
% uptime
Today
Networking
Operational
90 days ago
99.82
% uptime
Today
Wide Area Networking (WAN)
Operational
90 days ago
99.78
% uptime
Today
VPC Networking
Operational
90 days ago
99.66
% uptime
Today
Infiniband Networks
Operational
90 days ago
100.0
% uptime
Today
Datacenter Networking
Operational
90 days ago
99.85
% uptime
Today
Storage
Operational
90 days ago
99.99
% uptime
Today
Shared Disks
Operational
90 days ago
100.0
% uptime
Today
Persistent Storage
Operational
90 days ago
99.98
% uptime
Today
Orchestration
Operational
90 days ago
100.0
% uptime
Today
Crusoe Managed Kubernetes (CMK)
Operational
90 days ago
100.0
% uptime
Today
API
Operational
90 days ago
99.99
% uptime
Today
API
Operational
90 days ago
99.99
% uptime
Today
UI
Operational
90 days ago
99.99
% uptime
Today
UI
Operational
90 days ago
99.99
% uptime
Today
Container Registry
Partial Outage
90 days ago
99.47
% uptime
Today
Container Registry
Partial Outage
90 days ago
99.47
% uptime
Today
Managed Inference
Operational
90 days ago
99.83
% uptime
Today
Managed Inference
Operational
90 days ago
99.83
% 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.
Related
No incidents or maintenance related to this downtime.
Crusoe Cloud will be performing planned network maintenance to upgrade Front End (FE) Leaf switches across our global infrastructure. This critical update addresses known software bugs and standardizes our network command-set, significantly improving long-term stability and incident response.
During the maintenance window, all hypervisors in the us-east1-a region will experience intermittent unavailability. We strongly recommend pausing or gracefully shutting down critical workloads during the window to prevent unexpected disruptions or data loss.
All other services outside the us-east1-a region will remain operational. If you have questions regarding your specific workloads or notice persistent issues following a maintenance window, please reach out to support@crusoe.ai. Posted on
Jun 27, 2026 - 04:14 UTC
Crusoe Cloud will be performing planned network maintenance to upgrade Front End (FE) Leaf switches across our global infrastructure. This critical update addresses known software bugs and standardizes our network command-set, significantly improving long-term stability and incident response.
During the maintenance window, all hypervisors in the us-southcentral1-a region will experience intermittent unavailability. We strongly recommend pausing or gracefully shutting down critical workloads during the window to prevent unexpected disruptions or data loss.
All other services outside the us-southcentral1-a region will remain operational. If you have questions regarding your specific workloads or notice persistent issues following the maintenance window, please reach out to support@crusoe.ai. Posted on
Jun 27, 2026 - 04:16 UTC
Crusoe Cloud will be performing planned network maintenance to upgrade Front End (FE) Leaf switches across our global infrastructure. This critical update addresses known software bugs and standardizes our network command-set, significantly improving long-term stability and incident response.
During the maintenance window, all hypervisors in the eu-iceland1-a region will experience intermittent unavailability. We strongly recommend pausing or gracefully shutting down critical workloads during the window to prevent unexpected disruptions or data loss.
All other services outside the eu-iceland1-a region will remain operational. If you have questions regarding your specific workloads or notice persistent issues following a maintenance window, please reach out to support@crusoe.ai. Posted on
Jun 27, 2026 - 04:18 UTC
Past Incidents
Jul 8, 2026
Unresolved incident: Crusoe Container Registry (CCR) Outage – TLS/Auth Errors in US South Central(us-southcentral1-a).
Completed -
Scheduled maintenance has been completed successfully. Container Registry is back to normal operation.
Jul 1, 06:00 UTC
In progress -
Scheduled maintenance is currently in progress. We will provide updates as necessary.
Jul 1, 04:00 UTC
Scheduled -
Crusoe Cloud will be performing planned maintenance on the Crusoe Container Registry (CCR) in us-east1-a to improve reliability and performance. During the maintenance window, CCR in the us-east1-a region will be fully unavailable. We recommend pausing any workflows that depend on pushing or pulling container images until the window has concluded.
All other Crusoe Cloud services will remain operational. If you have questions regarding your specific workloads or notice persistent issues following the maintenance window, please reach out to support@crusoe.ai.
Jun 30, 21:10 UTC
Resolved -
A subset of resources in us-east1-a experienced intermittent external connectivity disruption during a planned network maintenance window. Affected workloads may have observed elevated latency, connection timeouts, or failures reaching external destinations. Virtual machine availability was not affected. The change was rolled back to restore connectivity, which was confirmed stable following the revert.
Jun 25, 09:30 UTC