Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Getting a Gemini API key is an exercise in frustration

ankursethi.com

Post reply on HN
Print view View original

351–360 of 361 posts

Re: Getting a Gemini API key is an exercise in frustration

#351

Post by logankilpatrick »

verdverm wrote: post #40
neom wrote: post #24

I complained about this on HN recently and Logan responded and asked me to email him with feedback on how I'd like the experience to work (I didn't, sorry Logan, been busy :)) - Logan, to his credit, is very active everywhere reading and soliciting feedback. I think they're going to be giving it a pretty big bump on ux/ui of AI studio next month. It's easy to see he's a super smart guy trying to build something compl…

I don't know, he announced on Bluesky that they are dropping a big vibe coding update to aistudio next year 1. cart out in front of the horse a bit on this one, lame hype building at best 2. Not at all what I want the team focusing on, they don't seem to have a clear mission Generally Google PMs and leaders have not been impressive or in touch for many years, since about the time all the good ones cashed out and star…

> cart out in front of the horse a bit on this one, lame hype building at best

hmmm

> 2. Not at all what I want the team focusing on, they don't seem to have a clear mission

allow anyone to build with Google's latest AI models, be the fastest path from prompt to production with Gemini

Re: Getting a Gemini API key is an exercise in frustration

#352

Post by logankilpatrick »

mvkel wrote: post #105
neom wrote: post #24

I complained about this on HN recently and Logan responded and asked me to email him with feedback on how I'd like the experience to work (I didn't, sorry Logan, been busy :)) - Logan, to his credit, is very active everywhere reading and soliciting feedback. I think they're going to be giving it a pretty big bump on ux/ui of AI studio next month. It's easy to see he's a super smart guy trying to build something compl…

This has often been the case (Google dev rel soliciting feedback) and they very rarely take meaningful action. Like firing a bug report with Apple. They'll get to it when it becomes strategically important to. Why making it easier to pay them isn't always strategically important, I'm not sure.

my team is responsible for building the worlds best product, every piece of feedback directly influences what we do : )

Re: Getting a Gemini API key is an exercise in frustration

#353

Post by logankilpatrick »

magicalhippo wrote: post #274
mvkel wrote: post #105

Earlier quoted context omitted.

This has often been the case (Google dev rel soliciting feedback) and they very rarely take meaningful action. Like firing a bug report with Apple. They'll get to it when it becomes strategically important to. Why making it easier to pay them isn't always strategically important, I'm not sure.

Dev rel is part of PR department isn't it? At least that's how it has always seemed to me when it comes to these mega corps.

nope, at least dev rel in deepmind is part of my product team

Re: Getting a Gemini API key is an exercise in frustration

#354

Post by logankilpatrick »

vinhnx wrote: post #123

A few months ago, I had a frustrating experience with the Gemini API while building an AI chat app as a side project. I registered through AI Studio and set up billing via Google Cloud Console, which offered a free trial with $200 in credits or 3 months of API usage. After deploying the Gemini API for my project, I navigated through the numerous settings in Google Cloud Console but forgot to set a billing limit. That…

we are bringing billing into AI Studio and adding hard caps by default so you don't overspend

Re: Getting a Gemini API key is an exercise in frustration

#355

Post by shresbm123 »

msp26 wrote: post #115

Hi if the Gemini API team is reading this can you please be more transparent about 'The specified schema produces a constraint that has too many states for serving. ...' when using Structured Outputs. I assume it has something to do with the underlying constraint grammar/token masks becoming too long/taking too long to compute. But as end users we have no way of figuring out what the actual limits are. OpenAI has mor…

Thanks for the feedback. Sorry that we closed the bug without giving you a clear indication of why. Let us look into this

Re: Getting a Gemini API key is an exercise in frustration

#356

Post by vinhnx »

logankilpatrick wrote: post #354
vinhnx wrote: post #123

A few months ago, I had a frustrating experience with the Gemini API while building an AI chat app as a side project. I registered through AI Studio and set up billing via Google Cloud Console, which offered a free trial with $200 in credits or 3 months of API usage. After deploying the Gemini API for my project, I navigated through the numerous settings in Google Cloud Console but forgot to set a billing limit. That…

we are bringing billing into AI Studio and adding hard caps by default so you don't overspend

Thank you, Logan! It's a very welcome change! Glad my comment reached you.

Re: Getting a Gemini API key is an exercise in frustration

#357

Post by thecupisblue »

logankilpatrick wrote: post #342
thecupisblue wrote: post #238

Earlier quoted context omitted.

Oh man let me add onto that! 4. If you read about a new Gemini model, you might want to use it - but are you using @google/genai, @google/generative-ai (wow finally deprecated) or @google-ai/generativelanguage? Silly mistake, but when nano banana dropped it was highly confusing image gen was available only through one of these. 5. Gemini supports video! But that video first has to be uploaded to "Google GenAI Drive"…

> 4. If you read about a new Gemini model, you might want to use it - but are you using @google/genai, @google/generative-ai (wow finally deprecated) or @google-ai/generativelanguage? Silly mistake, but when nano banana dropped it was highly confusing image gen was available only through one of these.? Yeah, I hear you, open to suggestions to make this more clear, but it is google/genai going forward. Switching packa…

Didn't catch in the updates that the custom FPS was released, amazing. Seems like the limit is just 20MB, but can use custom splitting for larger ones.

Trying to split all videos into frames was a PITA mostly due to weird inputs from different Android phones requiring handling all kinds of edge cases, then uploading each to Upload API with retry was also adding a lag + complexity, so doing it all in one go will save me both time and nerves (and tokens).

Thanks for listening and all the great work you do, since you came in the experience improved by an immeasurable amount.

Re: Getting a Gemini API key is an exercise in frustration

#358

Post by alisa_fortin »

thecupisblue wrote: post #238
Ozzie_osman wrote: post #145

I was recently (vibe)-coding some games with my kid, and we wanted some basic text-to-speech functionality. We tested Google's Gemini models in-browser, and they worked great, so we figured we'd add them to the app. Some fun learnings: 1. You can access those models via three APIs: the Gemini API (which it turns out is only for prototyping and returned errors 30% of the time), the Vertex API (much more stable but lac…

Oh man let me add onto that! 4. If you read about a new Gemini model, you might want to use it - but are you using @google/genai, @google/generative-ai (wow finally deprecated) or @google-ai/generativelanguage? Silly mistake, but when nano banana dropped it was highly confusing image gen was available only through one of these. 5. Gemini supports video! But that video first has to be uploaded to "Google GenAI Drive"…

Hi there! I am the PM for Veo on the Gemini API. I wanted to check with you on Point 8 - getting garbled sound when extending the video. Veo 3.1 is limited to the last 24 frames, 1s of video for the extension feature so sometimes dialog and audio are lacking continuity. We are working on this limitation. If you are experiencing a different issue altogether, would you be able to share the prompt so I can debug on my end? Thank you!

Re: Getting a Gemini API key is an exercise in frustration

#359

Post by quleap »

verdverm wrote: post #129
Leynos wrote: post #53

Earlier quoted context omitted.

They could always just use OpenCoder, Crush or Goose with OpenRouter ( https://openrouter.ai/google/gemini-3-pro-preview )

Google has the ADK project, which is really good. Python is the primary implementation, Java is there, Go is relatively new and aiming for parity. They could have contributed the Typescript implementation and built on common, solid foundation, but alas, the hydra's heads are not communicating well These other "frameworks" are (1) built by people who need to sell something, so they are often tied to their current thin…

ADK is anything but minimal. It indeed has too much abstraction. It's certainly designed to promote Google's own services. If you are looking for lightweight frameworks, consider smolagents or Pydantic AI. Even OpenAI Agents SDK is simpler. LangChain/LangGraph are the epitome of incompetent designs.

Re: Getting a Gemini API key is an exercise in frustration

#360

Post by johny115 »

you should try figuring out all Google products where you can generate images and videos, even attempt to learn how they work, how does billing work, where it uses credits from or API costs charged to where, what are the differences between all the weirdly named products (AI Studio, Vertex, Whisk, ImageFX, Veo Studio, Flow, etc.) with seemingly overlaping purposes

the product description of Whisk at https://labs.google/fx/ for example is "Whisk - Create some magic" ... wow, so obvious what it does

lot of fun ... especially considering this would be meant usually for non-engineer user

Google is bonkers for this ... takes an engineering degree to generate 4K Nano Banana Image outside of Gemini or even to begin understanding why VEO videos look different from each of their different products and why

the 3rd party platforms that use their API are 10x easier, put in credit card, choose model and settings, prompt and hit enter

Post reply on HN