Elastic.io incident

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

Major Resolved View vendor source →

Elastic.io experienced a major incident on April 20, 2026 affecting Elastic Inference Service, lasting 4h 4m. The incident has been resolved; the full update timeline is below.

Started
Apr 20, 2026, 06:37 AM UTC
Resolved
Apr 20, 2026, 10:41 AM UTC
Duration
4h 4m
Detected by Pingoru
Apr 20, 2026, 06:37 AM UTC

Affected components

Elastic Inference Service

Update timeline

  1. investigating Apr 20, 2026, 06:37 AM UTC

    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.

  2. investigating Apr 20, 2026, 09:50 AM UTC

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

  3. resolved Apr 20, 2026, 10:41 AM UTC

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