Agents
we're taking an early bet on open models specifically, because they're SO much cheaper one point of reference: an app outputting 10M tokens/…
we're taking an early bet on open models specifically, because they're SO much cheaper one point of reference: an app outputting 10M tokens/day costs roughly 250/day on Opus 4.8 versus ~24/day for Min
we're taking an early bet on open models specifically, because they're SO much cheaper one point of reference: an app outputting 10M tokens/day costs roughly 250/day on Opus 4.8 versus ~24/day for MiniMax M3 that's about $82k annual difference 🤯 https://x.com/masondrxy/status/2039768211554492420 let's assume agent = model + harness unfortunately, good models are getting really expensive! so you need a great harness to compensate. you can close the gap on agent performance by hill climbing w/ your harness, here's a guide on how to do just that! https://www.langchain.com/b…
Source: Harrison Chase (X) | 2026-06-04