Apr 6, 18:02 UTC
Resolved - This incident has been resolved.

Apr 6, 15:15 UTC
Monitoring - A fix has been implemented and we are monitoring the results.

Apr 6, 12:28 UTC
Investigating - Our Engineering team is investigating an issue with Serverless inference.

At this time, users may experience high error rates for open source models (llama 3.3 70b).

We apologize for the inconvenience and will share an update once we have more information.