Because many callers hang up about 10 seconds into a call, using a large LLM prompt can incur token costs even for calls that end early.

“Now that you're putting such a big, large prompt into your LLM,”

“you have to think about those calls where many people just hang up and predominantly calls just hang up 10 seconds into the call,”

“Now you're having to pay for all those tokens to just get inputted in.”