Scheduled maintenance: persistent storage and registry (US regions)
On Friday 6 November 2026 between 07:00 and 08:00 UTC we will carry out scheduled maintenance on persistent storage and the container registry in our US regions. During the window, reads and writes to persistent storage, image pulls and any new builds in progress may pause briefly, typically for a few seconds and no longer than a minute. Requests are held and complete once the pause ends rather than failing. Inference requests that do not use persistent storage are not affected, and EU persistent storage and the EU registry are not affected. No customer action is required. All other regions remain fully operational.
The latest update from Cerebrium.
State
Maintenance
Starts
Ongoing for
Not started
Worst impact
Maintenance
Updates
Times in UTCAs posted by Cerebrium
On Friday 6 November 2026 between 07:00 and 08:00 UTC we will carry out scheduled maintenance on persistent storage and the container registry in our US regions. During the window, reads and writes to persistent storage, image pulls and any new builds in progress may pause briefly, typically for a few seconds and no longer than a minute. Requests are held and complete once the pause ends rather than failing. Inference requests that do not use persistent storage are not affected, and EU persistent storage and the EU registry are not affected. No customer action is required. All other regions remain fully operational.
Affected components
3Cerebrium in the last 90 days
Full historyIncidents in 90 days
3
Days with an incident
3
Median duration
1 h 6 min
This incident
Not comparable
Other Cerebrium incidents
All incidents
Cerebrium·Nebius Clusters are unavailable
The issue with Nebius has been resolved and US and EU clusters are back online.
Cerebrium·Slow container image pulls in eu-north1
The issue has been resolved.
Cerebrium·Provider network outage: Nebius eu-north1
The issue has been resolved and the provider and region are stable again.
Follow Cerebrium
Your coding agent knows when Cerebrium is down, and tells you when a failure is theirs, not yours. You can also get Cerebrium incidents in a feed reader or in Slack.
Install the outages.live MCP server, so that when something breaks you can tell if the cause is a provider we depend on and not my code. It reads the official status pages of cloud, AI, payment and developer providers and gives you their incidents as MCP tools.
Add it as a remote MCP server named "outages" at https://outages.live/mcp (Streamable HTTP, no authentication), with your CLI command or your MCP config file.
Then:
1. Make sure it connects and shows the tools get_provider, list_feed and send_feedback.
2. Call get_provider with "cerebrium" and tell me if Cerebrium has a problem right now.
3. From now on, when a call to a third-party service fails or becomes slow, call get_provider for that service before you change my code.Paste this into any coding agent. It adds the server with its own MCP setup.
https://outages.live/feed.xml?providers=cerebrium/feed subscribe https://outages.live/feed.xml?providers=cerebriumFAQ
Go from tracking outages to fixing production issues with Polylane.
Try Polylane