Companies / Elastic Cloud / incidents

Elastic Cloud: Increased error rates for microsoft-multilingual-e5-large

Impact: majorStatus: resolvedStarted Resolved (4 d)4 updatesSource: stspg.io (opens in new tab)
Summary

Elastic Cloud reported a major incident starting 2026-08-13 08:32 UTC, lasting 4 days 3 h, with search embedding failures for microsoft-multilingual-e5-large due to upstream provider issues. Resolved 2026-08-17 11:40 UTC, the model was retired from Elastic Inference Service; requests now return errors, and customers must create custom inference endpoints using their own API keys.

Machine-written from the archived incident (Sol). Check the timeline before relying on it.

Timeline of updates

  1. investigating

    We are seeing elevated error rates from the upstream provider for the microsoft-multilingual-e5-large embedding model. Search embedding requests to this model may fail. We are investigating

  2. investigating

    We're seeing some improvement in availability but are continuing to monitor the situation. We will follow up with more information in due course.

  3. monitoring

    Unfortunately, we can no longer support the E5 Multilingual Large model on the Elastic Inference Service due to continued upstream provider issues. Any customers requiring this model should set up custom inference endpoints using their own API keys.

  4. resolved

    The microsoft-multilingual-e5-large model has been retired from the Elastic Inference Service. Requests to this model now return an error. Customers who wish to use this model with Elastic cloud must create a custom inference endpoint using their own API key. See our inference documentation for further details: https://www.elastic.co/docs/api/doc/elasticsearch/group/endpoint-inference

Rewindex changes for this incident

Impact, status and times are the vendor’s own, as last archived. View on stspg.io (opens in new tab). Elastic Cloud profile · Recent Elastic Cloud incidents · Markdown · JSON