Comment by IanCal

My base thing while advising people is that if anyone you pay needs to read the output, or you are directly replacing any kind of work then even frontier llm model inference costs are irrelevant. Of course you need to work out of that's truly the case but people worry about the cost in places where it's just irrelevant. If it's $2 when you get to an agent, each case that's avoided there could pay for around a million words read/generated. That's expensive compared to most API calls but irrelevant when counting human costs.