Live  /  Stability AI  /  Incident

Stability AI: Investigating elevated 500s for generation endpoints

Stability AI · stability.aiMajor incidentResolved2026-09-14 20:41 UTC
Public — what happened

Summary

Stability AI reported a major incident beginning at 16:33 UTC on 2026-09-14, when its generation API endpoints started returning an unusually high number of server errors (500s). By 16:52 UTC the company said it had found the cause, without describing it, and listed its API Platform, Brand Studio and Stable Audio products as affected. Stability AI said a fix was in place at 17:55 UTC and that it was watching the results. It declared the incident resolved at 20:41 UTC, saying all systems were working normally.

Timeline

Source of record: provider status page. Summary written by SquidGrid from the provider’s published updates; times in UTC.

Independent path health

The status page is the symptom. SquidGrid measures the paths that reach Stability AI against their own baselines — whether the routes carrying your traffic degraded, at which handoff, and who owns that stretch.

🔒 Sign in to see
Customers get the live Provider Assessment Report for Stability AI: its full incident track record, what tends to break, and recent public reports of problems.

Included with any paid plan.

Open the Stability AI report →

More from Stability AI

Covered in The Squid’s Ink, Week 39, 2026, our weekly internet health report.

The full archive is on the Stability AI status & history page.

Related: Stability AI status & history. SquidGrid is not affiliated with Stability AI.