@kmunson007
THANK GOD for this video! I have a descent amount of experience with AWS but these Google products are hard to figure out - what does what. Thank you and well done.
@ScottLangevin-w4j
Thanks for this information Victor. Very useful and appreciated.
@Billy-fo1hq
I think it's confusing because Google is in startup mode with AI. They are making many smaller companies (products) within the organisation to see which one has the most amount of market traction, both in eyeballs and in long-term profitability. The Google AI doesn't produce answers as good as ChatGPT, but the multimodal idea they have inside of Google AI studio has shown us what's truly possible with this technology. It's going to totally change the way we live our lives.
@helerionanastas4709
Thank you for the good information, short and precise!❤
@ivantan222
Very good explanation, so clear. 👍
@franklinchui6330
Hi, for Vertex AI, apart from the obvious lower pricing of the token rates (thanks to Victor) do note, Vertex AI being an enterprise platform in Google Cloud, model training, fine tuning, ...etc all need compute and storage too. These will come at some on-demand pricing on top of those token rates.
@lh24-g7l
thanks for the summary. Very helpful!
@pressrepeat2000
This is missing Gemini for Workspace. It has different compliance controls too and features, but I don’t know how exactly they work. I’m trying to find something that’s privacy compliant but doesn’t require me to use Google Cloud.
@affinitystablepeanuts
Thank you for this one! Was trying to "play with Gemini" and yeah... ended up finding all of these things at once which is... confusing. It's also fun that Google Ai Studio can show you pricing for usage of models, but at the same time it's.... free? Even for the latest ones? It's a bit weird.
@SlyProfits
so i just noticed no model is able to open a youtube link anymore, why is this, or am i missing something
@remain___
OMG thank you! Are people just supposed to know this stuff? Are we just supposed to not care?
@justtiredthings
I would be very grateful if you did a follow-up explaining and untangling the authentication mess associated with Vertex generative AI, because it is super confusing. I can hardly figure out how to maitain ongoing access for my own development process (without having to manually regenerate access tokens) for longer than like an hour, much less how to deploy a SaaS app that uses a Gemini model.
@mpitts87
OK so I am new to this whole thing. How do I ensure every member of my workspace has all the api abilities and can use all the app in the google cloud service? Thank you for the video very helpful in picking the one I need.
@AnujTaterh
Hello, for Vertex AI pricing, don't you think we need to convert characters into tokens - as per wesbite, Characters are counted by UTF-8 code points and white space is excluded from the count, resulting in approximately 4 characters per token
@DQ940
All the different names for everything is very confusing! I love google products but they do have a way of over-complicating things.
@101RealTalker
I just plain don't get it, maybe I am misunderstanding with fine-tuning means, maybe I don't even need this for my case usage... in the end I have one folder on my desktop with a measly 1.4 GB of markdown files that are totaling over 3 million words in research, that I want google pro 1.5 to represent as a mouthpiece. I guess the quickest way to explain it would be, master levels of needle in a haystack representation, I want it to be able to take all the files into macro context per each question, and give me a higher order perspective between the files that only artificial intelligence could possibly keep a wrangle of, comprehend? How on earth can I achieve this please!? Thank you.🙏
@adrianfeliperuedacastellan1705
Thank you so much for ths explanation
@bennguyen1313
Where would NotebookLM [Plus] fall into this? Is it strictly a chatbox (no API) that uses Gemini ? I heard getting a traditional API key out of the enterprise "Vertex" is nearly impossible.. but if you just go with standard Google Generative AI provider (Gemini , AI Studio), then it might be easiest to use a wrapper tool like Vercel AI SDK or OpenRouter. But do those services require a separate payment subscription.. or do you only need to pay them (I assume at a slightly higher price)? BTW, any thoughts on artificialanalysisAi?
@srinathpulaverthi853
Hi I'd like to correct an error you made regarding vertex AI being cheaper. Vertex AI charges per character in and out not tokens, ai studio however does it based on a token in token out. So your numbers are 4x lower than what will incur at the very least. And also for languages other than English the characters aren't what they look like. For example in telugu or hindi a same line as English would incur 3-6 times the cost either calculated via token or via character because the utf-8 encoding holds more characters per actual words in these scripts.
@vdantas