llama-3.3-70b-versatile Performance Issue

This incident has been resolved.

This incident has been resolved.

We have implemented a fix and are no longer seeing degraded output from llama-3.3-70b. The team is monitoring this model to ensure continued performance.

We have identified an issue where a small portion of requests against llama-3.3-70b-versatile are returning degraded output. A fix is in progress, Users may still see the issue until the fix is fully deployed.