Skip to main content
Elastic Cloud

EIS elevated 5xx error rates for model google-gemini-embedding-001

Partial outage Lasted 4h 5m · started · Elastic Cloud's page

Level
confirmed
Worst impact
Partial outage
Components
Elastic Inference Service
Down Index
31of 100

What to do

  • Check whether you use Elastic Cloud Elastic Inference Service. 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 4h 5m it lasted.

    Anything that failed between 2026-04-20 06:37 UTC and 2026-04-20 10:41 UTC may need a replay.
  • Subscribe to Elastic Cloud's feed to hear about the next one first. RSS feed

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

Updates from Elastic Cloud 3

  1. investigating

    We're seeing elevated 5xx error rates for the Gemini Embedding v1 model in EIS. The following default inference endpoint is affected: - .google-gemini-embedding-001 We're investigating and will update again in 2 hours or if there's a change in status.

    provider

  2. investigating

    Errors are coming from the provider API (Google). The incident has been escalated to them, and we are still waiting for a response.

    provider

  3. resolved

    An incident with an upstream service provider has been resolved, and access to the model is now restored.

    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-fabdae700c

Is Elastic Cloud still down?

No, this incident was resolved 2026-04-20 10:41 UTC. For Elastic Cloud's live state, see https://down.guide/elastic-cloud.

How long did it last?

4h 5m, from 2026-04-20 06:37 UTC to 2026-04-20 10:41 UTC, by the times Elastic Cloud posted.

What was affected?

Elastic Cloud named Elastic Inference Service.

What caused it?

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

Where does this come from?

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