When I test a bot running Claude Sonnet 4.6 and check the dashboard it says its been using GPT 5.1, but when I ran Grok 4.2 Reasoning it actually says Grok 4.2 Reasoning.
Is GPT 5.1 a fallback model and Claude is not actually running or is this a bug in the reporting system?
Message ID: 2737b903-d9dc-4dc0-af6b-a776e75ea861
Hi @hurmuli, thanks for posting! We are investigating this behavior - while we have been able to use Claude 4.6 without issue, we have seen reports that Message Insights is showing it listed as GPT 5.1. This is ticketed as PRD-638, and set to urgent in our system - I will post back here when I have some more answers!
Hi @hurmuli, this should be addressed now - please let me know if the issue is ongoing!
Seems the issue is fixed and now showing the correct model in reports.