Baseten: Elevated inference 500s for a subset of models deployed in 1 US-East cluster

Impact: majorStatus: resolvedStarted 2026-09-24 07:23 UTCResolved 2026-09-24 08:06 UTC (42 min)4 updatesSource: stspg.io

Summary

Baseten reported a major Dedicated Inference outage with elevated inference 500s affecting a subset of models in 1 US-East cluster. It started at 2026-09-24 07:23 UTC and was resolved at 2026-09-24 08:06 UTC, lasting 42 min; a fix was implemented at 07:48 UTC.

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

Affected components: Dedicated Inference

Timeline of updates

identified2026-09-24 07:23 UTC
The issue has been identified and a fix is being implemented.
monitoring2026-09-24 07:48 UTC
A fix has been implemented and we are monitoring the results.
monitoring2026-09-24 08:05 UTC
We are continuing to monitor for any further issues.
resolved2026-09-24 08:06 UTC
This incident has been resolved.

Rewindex changes for this incident

Major incident: Elevated inference 500s for a subset of models deployed in 1 US-East cluster 2026-09-24 07:23 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