Major incident
Elastic Cloud (Public): EIS elevated 5xx error rates for model google-gemini-embedding-001
Apr 20, 2026, 06:37 UTC
started
10:41 UTC
resolved
4 h 05 min
duration
Affected: Elastic Inference Service
Current status of Elastic Cloud (Public): Partial outage — live Elastic Cloud (Public) status
Timeline
- Apr 20, 2026, 06:37 UTCinvestigatingWe'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.
- Apr 20, 2026, 09:50 UTCinvestigatingErrors are coming from the provider API (Google). The incident has been escalated to them, and we are still waiting for a response.
- Apr 20, 2026, 10:41 UTCresolvedAn incident with an upstream service provider has been resolved, and access to the model is now restored.
Updates as published by Elastic Cloud (Public) (original).
More Elastic Cloud (Public) incidents
- October 23, 2026 Elastic Support Portal is unavailable
- October 22, 2026 403 error when trying to access Autoops in newly created serverless projects
- October 20, 2026 Elastic Cloud scaling issues in Azure
- October 20, 2026 Degraded availability for some Elastic Cloud Hosted and Serverless deployments in GCP europe-west2 (London)
- October 8, 2026 Delayed or Unavailable project operation in GCP us-central1
- October 6, 2026 Delayed Serverless Metrics in Azure UAE North region