Don't Put All Your Tokens in One Basket (theminimalistdeveloper.com) 1 points by rafaelnexus 2d ago ↗ HN
[–] turtleyacht 2d ago ↗ How do you prepare the fallback if it already took tokens to query the simpler model? [–] rafaelnexus 1d ago ↗ I don't know if I understood your question.
[–] plumman1 2d ago ↗ don't litellm and similar do this already? [–] rafaelnexus 1d ago ↗ Absolutely, a pretty good one. [–] santiago-pl 1d ago ↗ Actually, LiteLLM is the most popular, it was first product of this type, but there is plenty of more efficient and reliable alternate AI Gateways right now. I've written one - GoModel. https://gomodel.enterpilot.io/
[–] santiago-pl 1d ago ↗ Actually, LiteLLM is the most popular, it was first product of this type, but there is plenty of more efficient and reliable alternate AI Gateways right now. I've written one - GoModel. https://gomodel.enterpilot.io/
6 comments
[ 2.9 ms ] story [ 27.4 ms ] thread