N
Outage recap · Nebius

Nebius outage — October 2, 2026

On October 2, 2026, Nebius had 2 reported incidents on Nebius's official status page. Below is what was reported — impact, timing, and the AI services the same upstream outage could affect.

Issues with preempted Managed Kubernetes nodes in all regions

minor
Started
Oct 2, 11:31 AM EDT
Resolved
Oct 5, 11:54 AM EDT
Duration
72h 23m

Nebius's updates (3)

  1. investigating · Oct 2, 11:31 AM EDT

    We are investigating an issue affecting Managed Kubernetes node groups in all regions. Preemptible nodes that were in a preempted (stopped) state on October 1 or earlier do not auto-start when capacity becomes available. Manually stopping or starting a node group node does not take effect. Running workloads are not affected. A fix is being rolled out.

  2. identified · Oct 2, 11:50 AM EDT

    The issue has been identified and a fix has been prepared. The issue has limited impact and does not affect running workloads. To avoid possible disruption of customer production workloads over the weekend, deployment is scheduled for early next week. If you are experiencing any issues, please reach out to our support team, and we will be glad to assist you.

  3. resolved · Oct 5, 11:54 AM EDT

    This incident has been resolved.

What our checks recorded

We checked Nebius 576 times from Nebius's start time to its resolution, once every five minutes. Every one of them reached Nebius's site, so this incident did not show up as a failed page load. Our check loads the public site; it cannot see an API error or a broken feature. Median response time was 169 ms, against 147 ms over the 24 hours before. Nebius posted the incident at Oct 2, 11:31 AM EDT.

Updates are Nebius's own words from its status page (status: resolved); we never add an inferred cause. The vendor's incident page ↗

InfiniBand connectivity issues for GPU clusters in eu-west2

minor
Started
Oct 2, 10:30 PM EDT
Resolved
Oct 3, 4:59 AM EDT
Duration
6h 28m

Nebius's updates (4)

  1. investigating · Oct 2, 10:30 PM EDT

    We are investigating InfiniBand connectivity issues affecting some GPU clusters in Compute Cloud in eu-west2. Distributed training jobs on affected clusters may experience degraded interconnect performance or failures. We will provide an update as soon as we have more information.

  2. identified · Oct 3, 12:45 AM EDT

    We have identified the cause of the InfiniBand connectivity issues. Our on-site team is working to resolve it. We will provide an update as soon as we have more information.

  3. monitoring · Oct 3, 3:44 AM EDT

    A fix has been implemented and we are monitoring the results.

  4. resolved · Oct 3, 4:59 AM EDT

    This incident has been resolved.

What our checks recorded

We checked Nebius 77 times from Nebius's start time to its resolution, once every five minutes. Every one of them reached Nebius's site, so this incident did not show up as a failed page load. Our check loads the public site; it cannot see an API error or a broken feature. Median response time was 157 ms, against 146 ms over the 24 hours before. Nebius posted the incident at Oct 2, 10:30 PM EDT.

Updates are Nebius's own words from its status page (status: resolved); we never add an inferred cause. The vendor's incident page ↗

AIDownCheck is not affiliated with Nebius. This recap summarizes incidents published on Nebius's official status page.