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

Modal incidents, newest first, with date, duration and status.
DateIncidentDurationStatus
Aug 19, 2026Degraded latency on .spawn() calls106h 22mResolved
Aug 3, 2026Some services are downInvestigating
Jul 30, 2026Some services are down594h 36mResolved
Jul 24, 2026Flash Proxy (us-west) is down742h 55mResolved
Jul 23, 2026modal.com is degraded773h 48mResolved
Jun 29, 2026Storage degraded - impacting app creation1333h 5mResolved
Jun 16, 2026Image builds are down1648h 49mResolved
Jun 16, 2026Container scheduling / app deploys down1649h 15mResolved
Jun 16, 2026CLI volume operations disrupted1650h 47mResolved
Jun 3, 2026auth subsystem failures causing multiple issues1965h 4mResolved
Jun 1, 2026Database incident affecting services2009h 28mResolved
Jun 1, 2026Web endpoints and Image builds are down2010h 26mResolved
May 31, 2026Authorization System Restart30 minResolved
May 19, 2026CPU functions, GPU functions, and 5 other services are down1762h 21mResolved
May 11, 2026Storage refactor following AWS us-east-1c issues1h 30mResolved
May 8, 2026Internal data stores are failing2039h 29mResolved
May 7, 2026Container Scheduling and RPC errors2040h 1mResolved
May 7, 2026H200 Scheduling is degraded2043h 47mResolved

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.