Increased error rates for microsoft-multilingual-e5-large

What to do

• Check whether your product depends on Elastic Cloud. 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 4d 3h it lasted.

  Anything that failed between 2026-08-13 08:32 UTC and 2026-08-17 11:40 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 4

1. investigatingAug 13, 2026, 8:32 AM UTC

   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

   provider

2. investigatingAug 13, 2026, 2:45 PM UTC

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

   provider

3. monitoringAug 13, 2026, 6:26 PM UTC

   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.

   provider

4. resolvedAug 17, 2026, 11:40 AM UTC

   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

   provider

Corrections

None so far.

Something wrong on this page? Report an error or send us a note. Every fix is listed here.