Cerebrium outage history
We hold 17 Cerebrium incidents from Cerebrium's status page, the newest from Nov 11, 2026. 12 of the 17 listed carry Cerebrium's own update timeline. Each one links to a page with the vendor's updates and what our five-minute checks recorded while it was open.
Uptime & history
Tracking since Jun 22, 2026% of our checks that found Cerebrium fully operational — a degraded check counts against it, because a slow or partly-broken service is not a working one. Down and degraded time are counted at our 5-minute check resolution, so both are approximate. Longer windows fill in as data accrues — we never show uptime we haven't measured.
- Builds failingNov 11, 2026 → Nov 11, 2026 · resolved
- Scheduled maintenance: persistent storage and registry (US regions)Nov 6, 2026 → Nov 6, 2026 · resolved
- Nebius Clusters are unavailableOct 15, 2026 → Oct 15, 2026 · resolved
- Scheduled maintenance: US South Central cache tierOct 11, 2026 → Oct 11, 2026 · resolved
- Scheduled maintenance: cache tier in US East and US South CentralOct 4, 2026 → Oct 4, 2026 · resolved
- Scheduled provider maintenance: delayed GPU node provisioning in US East (Crusoe) and US South Central (CrusoeSep 10, 2026 → Sep 10, 2026 · resolved
- Slow container image pulls in eu-north1Sep 8, 2026 → Sep 8, 2026 · resolved
- Provider network outage: Nebius eu-north1Sep 2, 2026 → Sep 2, 2026 · resolved
- Upstream outage: us-central1Aug 19, 2026 → Aug 19, 2026 · resolved
- Emergency maintenance: Inference gatewayAug 13, 2026 → Aug 13, 2026 · resolved
- Networking issuesAug 3, 2026 → Aug 3, 2026 · resolved
- Scheduled Maintenance: Global router upgrade and Nebius image rolloutsAug 3, 2026 → Aug 3, 2026 · resolved
How Cerebrium fails
Since Jul 1, 2026, Cerebrium's status page has marked 11 Cerebrium components as impaired, across 812 of our five-minute readings. Build Service accounts for the most: 325 readings (about 27 hours) on 13 days, 117 of them marked as an outage rather than degraded, most recently on Nov 17, 2026. Next is US EAST 1, with 142 readings on 5 days. We hold 17 Cerebrium incidents from Cerebrium's status page, the earliest from Apr 29, 2026. Of the 15 that Cerebrium closed with an end time, the median lasted 2 h 58 min.
| Component | Outage | Degraded | Maint. | Days | Last |
|---|---|---|---|---|---|
| Build Service | 117 | 208 | 12 | 13 | Nov 17, 2026 |
| US EAST 1 | 6 | 136 | 42 | 5 | Jul 21, 2026 |
| US | 5 | 101 | 174 | 5 | Nov 6, 2026 |
| EU | — | 93 | 59 | 2 | Oct 15, 2026 |
| Docs | 57 | — | — | 1 | Sep 2, 2026 |
| Registry US EAST 1 | — | 54 | — | 2 | Jul 15, 2026 |
| Registry EU | — | 16 | — | 2 | Sep 8, 2026 |
| Global Routing | 6 | — | 11 | 1 | Aug 13, 2026 |
Incidents by month: Apr 2026: 1 · May 2026: 4 · Aug 2026: 4 · Sep 2026: 3 · Oct 2026: 3 · Nov 2026: 2
Counts are five-minute readings of Cerebrium's own component statuses, recorded only when a component is not operational. Hours are readings times five minutes, so a gap in our recording would undercount, never overcount.
Every recorded incident
November 2026 · 2
- Nov 11, 2026Builds failingresolved4 h 18 min2 updates
- Nov 6, 2026Scheduled maintenance: persistent storage and registry (US regions)resolved1 h2 updates
October 2026 · 3
- Oct 15, 2026Nebius Clusters are unavailableresolved17 min2 updates
- Oct 11, 2026Scheduled maintenance: US South Central cache tierresolved2 h2 updates
- Oct 4, 2026Scheduled maintenance: cache tier in US East and US South Centralresolved2 h2 updates
September 2026 · 3
- Sep 10, 2026Scheduled provider maintenance: delayed GPU node provisioning in US East (Crusoe) and US South Central (Crusoeresolved30 min2 updates
- Sep 8, 2026Slow container image pulls in eu-north1resolved1 h 6 min2 updates
- Sep 2, 2026Provider network outage: Nebius eu-north1resolved7 h 20 min2 updates
August 2026 · 4
- Aug 19, 2026Upstream outage: us-central1resolved5 h 7 min4 updates
- Aug 13, 2026Emergency maintenance: Inference gatewayresolved1 h2 updates
- Aug 3, 2026Networking issuesresolved2 h 58 min3 updates
- Aug 3, 2026Scheduled Maintenance: Global router upgrade and Nebius image rolloutsresolved4 h3 updates
May 2026 · 4
- May 28, 2026Inference Degraded in US East 1resolved3255 h 25 min
- May 19, 2026Unable to schedule workloads in crusoe us-east-1aresolvedend not published
- May 14, 2026Unable to schedule workloads on Crusoe (both regions)resolvedend not published
- May 13, 2026New builds broken in US Eastresolved2874 h 45 min
April 2026 · 1
- Apr 29, 2026Issue routing inference calls to newly deployed applicationsresolved3779 h 30 min
Incidents and their updates are Cerebrium's own words from its status page, recorded every five minutes; we never add an inferred cause. AIDownCheck is independent and not affiliated with Cerebrium.