AI Model Hub: Increased Error Rate

Incident Report for IONOS Cloud

Resolved

This incident has been resolved.

Posted Jun 01, 2026 - 17:06 UTC

Monitoring

The Mistral Small 24B Instruct model is currently experiencing a high load.
For users experiencing timeouts, we recommend switching to an alternative model, such as GPT-OSS-120B.

The slow response times previously observed in Collections are no longer occurring.

Posted May 29, 2026 - 22:31 UTC

Identified

We are currently experiencing significant load, which is affecting the response times of our Modelhub. Our team is working on removing performance bottlenecks.

Posted May 29, 2026 - 20:43 UTC

Investigating

We are currently investigating increased latency and error count in the AI Model Hub

Posted May 29, 2026 - 20:23 UTC

This incident affected: Global Services (AI Model Hub).