outages.live
Live
NebiusIncident · 2026-09-14 15:00 UTC

Managed Service for SkyPilot: cluster creation and update requests failing in eu-north1

ResolvedOfficial update

This incident has been resolved.

The latest update from Nebius.

State

Resolved

Started

48 d ago

2026-09-14 15:00 UTC

Lasted

24 h 33 min

until 2026-09-15 15:33 UTC

Worst impact

Partial outage

Timeline

3 updates
15:0021:0803:1609:2515:33
Partial outageUpdate postedTimes in UTC

Investigating

21 h 19 min 87%

Monitoring

3 h 14 min 13%

Updates

Times in UTC

As posted by Nebius

Resolved2026-09-15 15:33 UTC

This incident has been resolved.

Monitoring2026-09-15 12:19 UTC

The error rate has dropped to zero. Requests to create, update, start, and stop SkyPilot clusters in eu-north1 are completing successfully again. We are continuing to investigate the root cause and are monitoring the service closely. Instances that were already running have not been affected at any point. We will provide a further update as the investigation progresses.

Investigating2026-09-14 15:00 UTC

We are investigating an issue affecting Managed Service for SkyPilot in eu-north1. Requests to create or update SkyPilot clusters, as well as start and stop requests, are failing with HTTP 503 errors. Instances that are already running are not affected and continue to operate normally.

Affected components

2
Managed Service for SkyPilotEU-NORTH1 - Managed Service for SkyPilot

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.

Prompt
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.

RSS
https://outages.cc/feed.xml?providers=nebius
Slack
/feed subscribe https://outages.cc/feed.xml?providers=nebius

FAQ

Go from tracking outages to fixing production issues with Polylane.

Try Polylane