If you’ve spent any time with the vertex LLM apis you wouldn’t be so enthusiastic about using Google’s platform (I say this as someone who prefers GCP to aws for compute and networking).

been using it for years, no idea what you are getting at

I've never had the downtime or service busy situations I've heard others complain about with other vendors.

They did pricing based on chars back in the day, but now they are token based like everyone else.

I like that they are building custom hardware that is industry leading in terms of limiting how much my AI usage impacts the environment.

What do you think I shouldn't be enthusiastic about?