Changes / Baseten / Elevated inference 500s for models in a single US-based cluster

Baseten: Major incident: Elevated inference 500s for models in a single US-based cluster

Summary

Baseten reported a major Dedicated Inference incident with elevated inference 500s for models in a single US-based cluster. It ran from 2026-08-31 06:38 UTC to 2026-08-31 07:02 UTC (24 min); a fix was in place and traffic was back at 06:57 UTC.

Machine-written from the diff below (Sol; type: incident outage). Check the diff before relying on it.

Major incidentLabel: outage (model (Jev), 97%)Changed Detected Source: stspg.io

What changed

AddedTitle#1
Before: not present
After: Elevated inference 500s for models in a single US-based cluster
AddedImpact#2
Before: not present
After: major
AddedStatus#3
Before: not present
After: resolved
AddedStart time#4
Before: not present
After: 2026-08-31 06:38 UTC
AddedResolved time#5
Before: not present
After: 2026-08-31 07:02 UTC
AddedAffected components#6
Before: not present
After: Dedicated Inference
AddedUpdateinvestigating#7
Before: not present
After: We are currently investigating this issue.
AddedUpdatemonitoring#8
Before: not present
After: Fix is in place and traffic is back.
AddedUpdateresolved#9
Before: not present
After: This incident has been resolved.

First version of this incident archived by Rewindex. View the live incident.

History of this incident

When (UTC)ChangeKind
Major incident: Elevated inference 500s for models in a single US-based cluster (this change)
Baseten reported a major Dedicated Inference incident with elevated inference 500s for models in a single US-based cluster. It ran from 2026-08-31 06:38 UTC to 2026-08-31 07:02 UTC (24 min); a fix was in place and traffic was back at 06:57 UTC.
Major incident

All Baseten changes → · Baseten profile · Markdown · JSON