Vellum Outage History
16 incidents recorded over the last 365 days, 16 of them resolved. Durations are measured from when PulsAPI first saw the problem to when it cleared, which is usually longer than the vendor's own figure.
Every Recorded Vellum Incident
| Date | Incident | Duration | Status |
|---|---|---|---|
| Sep 1, 2026 | Platform network instabilityThis incident has been resolved. | 3h 48m | Resolved |
| Feb 3, 2026 | Vector database downtime affecting searchThis incident has been resolved. | 12 min | Resolved |
| Jan 27, 2026 | Increased latency on predict endpointThis incident has been resolved. | 44 min | Resolved |
| Jan 27, 2026 | Increased latency on predict endpointThis incident has been resolved. | 18 min | Resolved |
| Jan 19, 2026 | Users unable to log in to app.vellum.aiThis incident has been resolved. | 27 min | Resolved |
| Jan 9, 2026 | Increased Workflow Execution LatencyThis incident has been resolved. | 2h 12m | Resolved |
| Jan 8, 2026 | Vellum webapp outageThis incident has been resolved. | 2h 43m | Resolved |
| Jan 8, 2026 | Vellum webapp outageThe Vellum webapp experienced an outage for 6 minutes as a result of an infrastructure issue | 0 min | Resolved |
| Dec 18, 2025 | API's and Web App downThis incident has been resolved. | 16 min | Resolved |
| Dec 8, 2025 | Monitoring OutageThis incident has been resolved. | 42 min | Resolved |
| Nov 28, 2025 | Vellum Web UI is DownThis incident has been resolved. | 8 min | Resolved |
| Nov 26, 2025 | Vellum Frontend Was DownThe Vellum Frontend failed to load for 4 minutes from 5:11pm EST to 5:15pm EST. No backend services or APIs were affected | -18 min | Resolved |
| Nov 21, 2025 | Vellum App and API is DownThis incident has been resolved. | 30 min | Resolved |
| Nov 18, 2025 | Downstream Cloudflare Issues DetectedThis incident has been resolved. | 4h 4m | Resolved |
| Nov 13, 2025 | Claude model request compilation errorsFor a brief period, some requests to a subset of Claude models failed due to the addition of a new feature which has been reverted | -35 min | Resolved |
| Nov 5, 2025 | Users unable to create workflow sandboxesThis incident has been resolved. | 43 min | Resolved |
Hear about the next one while it is open
Everything above is a record written after the fact. We can email you when the next Vellum incident opens instead, at the point where knowing still changes what you do.
Free, no password, no card. Unsubscribe in one click.
How to Read This Vellum Incident Log
Each row is an incident PulsAPI observed, not a summary written afterwards. The duration is wall-clock time between the first failing check and the first clean one, so it includes the window before Vellum acknowledged anything. Vendor post-mortems typically measure from acknowledgement, which is why their numbers are usually shorter.
Incidents still open have no duration yet and are listed as ongoing rather than being given a running total. The archive covers the last 365 days; anything older has aged out of the window rather than never having happened.
The longest single Vellum outage in this window ran 4h 4m, against a mean recovery of 1h 12m. If you depend on Vellum in a customer-facing path, the longest figure is the one to design around. The mean is what happens on a normal bad day; the maximum is what happens on the worst one.