Thread

1. minimaxir · 1790702170 · focus · HN ↗

   > Cached input costs just $0.10 per million tokens—95% less than standard input pricing and 50% less than GPT‑6 Sol’s cached input pricing

   This is the actual big announcement. 50% cheaper cache than GPT-6 Sol will get you far more mileage on Codex.

   1. joshstrange · 1790703602 · focus · HN ↗

      > 50% cheaper cache than GPT-6 Sol will get you far more mileage on Codex.

      Cache doesn't help you much when you are compacting every 5 minutes...

      I was shocked at how quickly I ran out my $100/mo subscription with a single agent (sol medium).

      1. KetoManx64 · 1790931880 · focus · HN ↗

         Do you just keep one conversation going for all projects? That's the only way I've seen other people in my company burn through all their tokens.

         Everyone else that uses memory files and a new conversation for each new sub project/feature rarely hit their weekly allotments.

Unofficial Hacker News client; not affiliated with Y Combinator.