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. sscaryterry · 1790704326 · focus · HN ↗

      [dead]

      1. minimaxir · 1790704777 · focus · HN ↗

         if an openai employee is reading this plz hire me i am unemployed and i need a job

         (Usage limits are entirely dependent on what you're doing with them. If you're not running it on 1 million LoC codebases you can get a lot of mileage out of even a 5x account particularly with the recent cheap models)

Unofficial Hacker News client; not affiliated with Y Combinator.