hi there, Just for one message and tool calling it cost us close to 2$. That seems to be too expensive. Can you please help check the logs and let us know if we are doing something wrong or not? The log id is 6eccd32e-677e-4dda-a0e9-c18e01cb8004. Thanks Regards, Appu

Looking into it

Hey! To help track down this issue, could you share: - The call ID This would really help us figure out what went wrong!

it was not a call. it was a chat session on the VAPI dashboard

Your chat ID

Hey Appu, a gentle reminder to continue this thread.

this is the 6eccd32e-677e-4dda-a0e9-c18e01cb8004 chat ID, i had shared in the first messages as well

Looking into it

thanks

Breakdown

json
  [
    {
      "type": "model",
      "model": {"model": "gpt-4o", "provider": "openai"},
      "cost": 1.98558,
      "promptTokens": 396720,
      "completionTokens": 132
    },
    {"type": "chat", "cost": 0.005}
  ],

Total Cost

1.9906 - 396K prompt tokens from massive tool responses (hotel search returned 25+ hotels with full details, room search with pricing/policies) - Only 132 completion tokens , efficient AI responses - Context accumulated as conversation progressed through search → selection → booking

so the previous tool response has created this issue, understood

Marking this ticket as Solved ✅