Is there a guide for when to use sml, med or lrg for messages?

[lukek]

Can someone give me an example of when it’s best suited to use small vs medium vs large for the messages? Is there a guide that already exists, if so where can I find it?

Thanks

Just want to see how to optimise the messages in that regard.

[anshumanb (Anshuman Bhardwaj)]

Hi @lukek, yes. @jacobparis recently penned down a community post about this very topic:

Choose the right v0 model for each task

There are currently 3 different models available on v0 v0-1.5-sm ($0.50 / million tokens) v0-1.5-md ($1.50 / million tokens) v0-1.5-lg ($7.50 / million tokens) These aren’t real models in the conventional sense, but instead are composite models that combine base models with refinements to improve code quality output [image] small model Use the small model for edits and Q&A All three of the models get the same specialized data which means the small model is just as good at answering genera…

I hope you find it helpful.

[lukek]

I was struggling with a persistent issue. What made it worse is it’s related to Supabase integration which adds complexity.

I saw your comment and read through Jacob’s post about which model size to use. Then after a few more failed attempts I decided to experiment with medium and large model size and now it seems to be working.

Im sure the internal is super messy but I now have progress, great, relief, improvement