Skip to main content
Baseten

Elevated inference 500s for models in 1 cluster due to cloud provider outage

Degraded Lasted 15m · started · Baseten's page

Level
confirmed
Worst impact
Degraded
Components
Dedicated Inference
Down Index
16of 100

What to do

  • Check whether you use Baseten Dedicated Inference. Check your stack

    Paste a package.json, lockfile, Terraform or a list of domains at down.guide/stack to see every provider you depend on.
  • Confirm your retries, queues and scheduled jobs caught up after the 15m it lasted.

    Anything that failed between 2026-06-27 06:35 UTC and 2026-06-27 06:50 UTC may need a replay.
  • Subscribe to Baseten's feed to hear about the next one first. RSS feed

    https://down.guide/feed?provider=baseten works in Slack (/feed subscribe), Discord feed bots and any RSS reader.

Updates from Baseten 3

  1. identified

    The issue has been identified and a fix is being implemented.

    provider

  2. monitoring

    Models are auto-moving to other clusters

    provider

  3. resolved

    This incident has been resolved.

    provider

Reports count in aggregate; nothing about you is shown.

Corrections

None so far.

Something wrong on this page? Report an error or send us a note. Every fix is listed here.

Questions about DWN-4f9d79b811

Is Baseten still down?

No, this incident was resolved 2026-06-27 06:50 UTC. For Baseten's live state, see https://down.guide/baseten.

How long did it last?

15m, from 2026-06-27 06:35 UTC to 2026-06-27 06:50 UTC, by the times Baseten posted.

What was affected?

Baseten named Dedicated Inference.

What caused it?

Baseten hasn't published a root cause. If it does, it shows here.

Where does this come from?

Baseten's official status page, https://status.baseten.co, quoted verbatim. down.guide's own probes, reports and social counts are labeled as ours.