Modal Outage History
18 incidents recorded over the last 365 days, 17 of them resolved, 1 still open. 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 Modal Incident
| Date | Incident | Duration | Status |
|---|---|---|---|
| Aug 19, 2026 | Degraded latency on .spawn() calls | 106h 22m | Resolved |
| Aug 3, 2026 | Some services are down | — | Investigating |
| Jul 30, 2026 | Some services are down | 594h 36m | Resolved |
| Jul 24, 2026 | Flash Proxy (us-west) is down | 742h 55m | Resolved |
| Jul 23, 2026 | modal.com is degraded | 773h 48m | Resolved |
| Jun 29, 2026 | Storage degraded - impacting app creation | 1333h 5m | Resolved |
| Jun 16, 2026 | Image builds are down | 1648h 49m | Resolved |
| Jun 16, 2026 | Container scheduling / app deploys down | 1649h 15m | Resolved |
| Jun 16, 2026 | CLI volume operations disrupted | 1650h 47m | Resolved |
| Jun 3, 2026 | auth subsystem failures causing multiple issues | 1965h 4m | Resolved |
| Jun 1, 2026 | Database incident affecting services | 2009h 28m | Resolved |
| Jun 1, 2026 | Web endpoints and Image builds are down | 2010h 26m | Resolved |
| May 31, 2026 | Authorization System Restart | 30 min | Resolved |
| May 19, 2026 | CPU functions, GPU functions, and 5 other services are down | 1762h 21m | Resolved |
| May 11, 2026 | Storage refactor following AWS us-east-1c issues | 1h 30m | Resolved |
| May 8, 2026 | Internal data stores are failing | 2039h 29m | Resolved |
| May 7, 2026 | Container Scheduling and RPC errors | 2040h 1m | Resolved |
| May 7, 2026 | H200 Scheduling is degraded | 2043h 47m | Resolved |
How to Read This Modal 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 Modal 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 Modal outage in this window ran 85d 3h, against a mean recovery of 54d 20h. If you depend on Modal 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.