Show HN: Frugon – Find which LLM calls a cheaper model could handle (local, MIT)
Hi HN. I built Frugon to answer one question on my own machine: which of my LLM calls could I run through a cheaper model and stretch my dollar without losing quality? I started leaning in heavily on AI this year and my tokens kept running out mid week...sometimes within a couple of days, because I didn't want to miss out on whatever edge the expensive model had over the cheaper one. So I started tracking my cost per task type, and realised a decent chunk of my cost was going to searches/scans,
