Token Factory 503 errors in eu-west2
The issue has been resolved.
The latest update from Nebius.
State
Resolved
Started
8 d ago
2026-10-24 13:22 UTC
Lasted
1 h 2 min
until 2026-10-24 14:24 UTC
Worst impact
Partial outage
Timeline
3 updatesInvestigating
43 min 69%
Monitoring
19 min 31%
Updates
Times in UTCAs posted by Nebius
The issue has been resolved.
Some customers receive 503 errors from Token Factory dedicated endpoints in eu-west2. We have identified the cause and applied the fix. The team is monitoring the results.
Some customers receive 503 errors from Token Factory endpoints in eu-west2. We are investigating and determining the full scope of the issue.
Affected components
2Nebius in the last 90 days
Full historyIncidents in 90 days
27
Days with an incident
27
Median duration
1 h 18 min
This incident
20% shorter than the median
Other Nebius incidents
All incidentsNebius·Token Factory: some dedicated endpoints partially unavailable
This incident has been resolved.
Nebius·Compute Cloud: disk images and snapshots partial unavailability
The incident has been resolved
Nebius·Partial IAM and console unavailability
The console and IAM were unavailable for approximately 10 minutes. The incident has been mitigated, and service availability has been restored.
Nebius·CLI login issues
This incident has been resolved.
Nebius·InfiniBand connectivity issues for GPU clusters in eu-west2
This incident has been resolved.
Follow Nebius
Your coding agent knows when Nebius is down, and tells you when a failure is theirs, not yours. You can also get Nebius 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.cc/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 "nebius" and tell me if Nebius 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.cc/feed.xml?providers=nebius/feed subscribe https://outages.cc/feed.xml?providers=nebiusFAQ
Go from tracking outages to fixing production issues with Polylane.
Try Polylane