Changes / Elastic Cloud / EIS elevated 5xx error rates for model google-gemini-embedding-001
Elastic Cloud: Major incident: EIS elevated 5xx error rates for model google-gemini-embedding-001
Summary
Elastic Cloud reported a major Elastic Inference Service incident affecting .google-gemini-embedding-001, with elevated 5xx errors starting at 2026-04-20 06:37 UTC and lasting 4 h 4 min. Errors came from Google's provider API; the upstream incident was resolved and model access restored at 2026-04-20 10:41 UTC.
Machine-written from the diff below (Sol; type: incident outage). Check the diff before relying on it.
What changed
Before: not present
After: EIS elevated 5xx error rates for model google-gemini-embedding-001
Before: not present
After: major
Before: not present
After: resolved
Before: not present
After: 2026-04-20 06:37 UTC
Before: not present
After: 2026-04-20 10:41 UTC
Before: not present
After: Elastic Inference Service, Global services - Elastic Inference Service
Before: not present
After: 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.
Before: not present
After: Errors are coming from the provider API (Google). The incident has been escalated to them, and we are still waiting for a response.
Before: not present
After: An incident with an upstream service provider has been resolved, and access to the model is now restored.
First version of this incident archived by Rewindex. View the live incident (opens in new tab).
History of this incident
| When (UTC) | Change | Kind |
|---|---|---|
| Major incident: EIS elevated 5xx error rates for model google-gemini-embedding-001 (this change) Elastic Cloud reported a major Elastic Inference Service incident affecting .google-gemini-embedding-001, with elevated 5xx errors starting at 2026-04-20 06:37 UTC and lasting 4 h 4 min. Errors came from Google's provider API; the upstream incident was resolved and model access restored at 2026-04-20 10:41 UTC. | Major incident |
All Elastic Cloud changes → · Elastic Cloud profile · Markdown · JSON