At 2025/09/29 20:39:30 UTC, Runpod's primary API suffered an outage. This was due to an upstream vendor's managed database offering suffering an internal critical error. Vendor support was engaged immediately and their team was able to perform recovery at 2025/09/29 21:26:30. During the outage period, all calls made to the REST/GraphQL API's/console UI did not respond correctly and a percentage of serverless API job submissions were impacted. Existing pod workloads and data was not impacted. At this time all services are operating normally and all global capacity is available. We are engaging with the vendor to determine the root cause.

Upstream resolved their issue and we are back to operating normally.

We are seeing some preliminary recovery. We are continuing work through and monitor the situation.

There is an upstream component related issue. We are working through on resolving this issue.

Console data not showing up on the dashboard. We are investigating and working on resolving the issue.