Baseten: Elevated inference 500s for a subset of models deployed in GCP central1

Impact: majorStatus: resolvedStarted 2026-09-21 18:34 UTCResolved 2026-09-21 18:41 UTC (7 min)3 updatesSource: stspg.io

Summary

Baseten reported a major Dedicated Inference incident causing elevated inference 500s for a subset of models deployed in GCP central1. It started at 2026-09-21 18:34 UTC and was resolved at 2026-09-21 18:41 UTC, with a computed duration of 6 min; a fix was implemented by 18:38 UTC.

Machine-written from the archived incident (Sol). Check the timeline before relying on it.

Affected components: Dedicated Inference

Timeline of updates

identified2026-09-21 18:34 UTC
The issue has been identified and a fix is being implemented.
monitoring2026-09-21 18:38 UTC
A fix has been implemented and we are monitoring the results.
resolved2026-09-21 18:41 UTC
This incident has been resolved.

Rewindex changes for this incident

Major incident: Elevated inference 500s for a subset of models deployed in GCP central1 2026-09-21 18:34 UTC

Impact, status and times are the vendor’s own, as last archived. View on stspg.io (opens in new tab). Baseten profile · Recent Baseten incidents · Markdown · JSON