Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Write a detailed plan using a more expensive model and implement it using the cheaper one.


How much are you saving once the more expensive model already has all the context loaded and ready to go?


API calls get more expensive, not less, as you've loaded more context. This is exactly when you want to switch to cheaper models.


There is caching to consider. Switching models throws away the cached tokens.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: