Hi Vapi team, We’ve noticed an issue where one of our assistant calls was unexpectedly routed through multiple LLM providers, which caused unusually high costs. Details: Call ID: 653fbd91-fa0b-4758-a6dd-b067947b6f8f Org ID: 21c685b6-4054-43c6-8a20-157334ca216e Date/Time: Aug 26, 01:30 UTC Duration: ~2 minutes Cost: $2.39 (unexpectedly high for such a short call) Issue Observed: From the logs, I can see that during this single call, Vapi made requests to different providers/models: azure-openai → gpt-4-1106-preview azure-openai → gpt-4-0125-preview openai → chatgpt-4o-latest This looks like multiple model invocations happened for the same call, instead of sticking to a single provider/model configuration. Could you please investigate why this call routed through multiple LLMs? https://cdn.discordapp.com/attachments/1409957956707024936/1409957957654941746/2025-08-26_20.46.04.png?ex=68af452c&is=68adf3ac&hm=722fd1f75cdbf10c5dd3f8174dcf0d9694c175cedbf084dc8a7d329c9a6d0679& https://cdn.discordapp.com/attachments/1409957956707024936/1409957958393004065/2025-08-26_20.46.12.png?ex=68af452d&is=68adf3ad&hm=b76413b6dab390ce1ba920cf390921225af8d16f4f831db258368e577dcb73dd& https://cdn.discordapp.com/attachments/1409957956707024936/1409957958737203220/2025-08-26_20.46.29.png?ex=68af452d&is=68adf3ad&hm=16529bfdc145b2764d8081de5ad00c83cd01606c18b59b9a0391d8d0078839c9& https://cdn.discordapp.com/attachments/1409957956707024936/1409957959139594422/2025-08-26_20.46.53.png?ex=68af452d&is=68adf3ad&hm=bb8f57bcb5f7ce9678d8ea72e16434e5b34a01ca4025a0ee02ace7611f7e81d8&

Hey Yaroslav, thanks for sharing your details. Our team will look into it and get back to you soon with an update.