Expected responses from LLM Gateway using Claude models

We have continued to see good performance since releasing the earlier fix and are now marking this issue as resolved.

We have released a fix that has resolved the unexpected responses we were seeing when Claude models were used. Everything is working normally now, but we will continue to monitor traffic to ensure continued good performance.

We have identified the root cause of this issue and are working to release a fix.

We are currently investigating an issue with LLM Gateway that is causing unexpected responses when using Claude models. This issue is not affecting LLM Gateway requests using other models. We are working to identify and resolve the root cause of these issues.