Oh man, there is so, so much pain here. Random example - if GOOGLE_GENAI_USE_VERTEXAI=true in your environment, woe betide you if you're trying to use gemini cli with an API key. Error messages don't match up with actual problems, you'll be told to log in using the cli auth for google, then you'll be told your API keys have no access.. It's just a huge mess. I still don't really know if I'm using a vertex API key or a non-vertex one, and I don't want to touch anything since I somehow got things running..
Anyway vai com dios, I know that there's a fundamental level of complexity deploying at google, and deploying globally, but it's just really hard compared to some competitors. Sadly, because the gemini series is excellent!
Thank you for your service. Also, one of the main issues from the outside seems to me to be the impedance mismatch between google's entire cloud business and the direct-to-dev type API access oAI and Anthropic have pioneered. So, there's always going to be some pain here. It would be realllyy nice if that pain were incurred internally at the mothership, both for Dev UX and for sales. But so far, it looks to me like it's being spread out internally and externally.
Anyway vai com dios, I know that there's a fundamental level of complexity deploying at google, and deploying globally, but it's just really hard compared to some competitors. Sadly, because the gemini series is excellent!