The closest to an authoritative source on it is https://twitter.com/sama/status/1599671496636780546
> average is probably single-digits cents per chat; trying to figure out more precisely and also how we can optimize it
An attempt to work through it from related resources is https://twitter.com/tomgoldsteincs/status/160019698195510069...
In particular https://twitter.com/tomgoldsteincs/status/160019699090561433...
> So what would this cost to host? On Azure cloud, each A100 card costs about $3 an hour. That's $0.0003 per word generated.
> But it generates a lot of words! The model usually responds to my queries with ~30 words, which adds up to about 1 cent per query.
---
It is much less than $1/interaction.
The closest to an authoritative source on it is https://twitter.com/sama/status/1599671496636780546
> average is probably single-digits cents per chat; trying to figure out more precisely and also how we can optimize it
An attempt to work through it from related resources is https://twitter.com/tomgoldsteincs/status/160019698195510069...
In particular https://twitter.com/tomgoldsteincs/status/160019699090561433...
> So what would this cost to host? On Azure cloud, each A100 card costs about $3 an hour. That's $0.0003 per word generated.
> But it generates a lot of words! The model usually responds to my queries with ~30 words, which adds up to about 1 cent per query.
---
It is much less than $1/interaction.