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

321–330 of 361 posts

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

#321

Post by polalavik »

TheTaytay wrote: post #154
polalavik wrote: post #35

Earlier quoted context omitted.

holy hell google cloud is so confusing i just ended up using (a much more expensive) digital ocean droplet instead for a little project. I guess they only really care about enterprise customers who can burn tons of money figuring it out, but it made me never want to use it again. Same with google ads - super fuckin shit UI/UX, super confusing to understand what is going on. companies like digital ocean, supabase, etc…

Well said. I’m literally afraid of the cloud console dashboards from the big providers. That’s especially true with the quagmire that is AWS. It’s so easy to leave a resource turned on that you are no longer using, and so hard to tell which resource belongs to which project, or have high confidence you set up permissions correctly. They have multiple products whose only job is to monitor and configure your AWS accoun…

This 1000%. The Ui is so convoluted I’m scared that I’ll leave something on and be charged a fortune.

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

#322

Post by btown »

numlocked wrote: post #272
btown wrote: post #82

In case it's helpful to anyone, https://openrouter.ai/google/gemini-3-pro-preview is useful to know about. Adding another layer on top of Google's own APIs adds latency, lowers reliability, and (AFAIK) doesn't allow batch mode - but if that's tolerable, it avoids the mess that is Google Service Account JSON and Cloud Billing.

(I work at OpenRouter) We add about 15ms of latency once the cache is warm (e.g. on subsequent requests) -- and if there are reliability problems, please let us know! OpenRouter should be more reliable as we will load balance and fall back between different Gemini endpoints.

Is batch mode on the roadmap? As the frontier model providers start to think more and more about profitability, and prices/latencies rise as a result, I can see batching becoming more and more necessary for many use cases.

Would love to know we can build against the OpenAI batch API and (soon?) have a path towards being model-agnostic.

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

#323

Post by kldg »

cortesoft wrote: post #31
dannyobrien wrote: post #11

The odd thing about all of this (well, I guess it's not odd, just ironic), is that when Google AdWords started, one of the notable things about it was that anyone could start serving or buying ads. You just needed a credit-card. I think that bought Google a lot of credibility (along with the ads being text-only) as they entered an already disreputable space: ordinary users and small businesses felt they were getting…

I have had way too many arguments over the years with product and sales people at my job on the importance of instant self-signup. I want to be able to just pay and go, without having to talk to people or wait for things. I know part of it is that sales wants to be able to price discriminate and wants to be able to use their sales skills on a customer, but I am never going to sign up for anything that makes me talk t…

Bless you and your family for all time and beyond. Having to talk to someone before I even get a price to compare, or a demo, drives me mad, and then a week later you get their contract and find they claim ownership of everything your company uploads to them -- all that time down the drain, and the salesperson never read the contract so they don't know what to say. Then there are the smaller companies with unwritten policies -- we used to get call metric software from a small Swiss outfit, but I discovered we were billed based on how many employees we've ever had, not based on current employees, with no method to delete terminated employees from the database -- on what planet do you expect someone to pay a recurring expense in perpetuity for someone who showed up for training one day 5 years ago and was never heard from again? I was so mad when they gave us the renewal price, we made our own replacement software for it.

Anyway, long story short: I now require the price and details before I'll even consider talking to a salesperson, not the other way around. Might actually be a good job for an AI agent; they can talk to these sales bozos (respectfully) for me.

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

#324

Post by nicbou »

sceptic123 wrote: post #290
nicbou wrote: post #285

Earlier quoted context omitted.

Nope. I built a calculator for that last year and ooooh boy. Now I pipe half the requests to a human because of all the possible mistakes a person can make. It's crazy complicated. Finding that human is also hard because of the perverse incentives to sell more lucrative products.

That's my point, you need to be a specialist to understand it, but the specialists are incentivised to upsell you. A simpler product would be better for consumers, but won't happen because there are industries (and a lot of lobbying) built up around keeping the money train rolling.

Not really. Some things are just complex.

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

#325

Post by rozap »

Filligree wrote: post #270
alexp2021 wrote: post #233

Earlier quoted context omitted.

Exactly the same for me. Quote usage is something like 2%, but constantly experience the quota limit error.

The trick here is that they describe internal loadshedding as quota limits. There’s a quote for your general class of query, and there’s a quota for how many can be in flight on a given server. It’s not necessarily about you specifically.

This was the vibe I got, that they were actually just load shedding but writing it as a 429 with a message about the quota being hit. And if they need to load shed, fine, I get it, but it is a waste of time for me to go in circles trying to figure out wtf is wrong when they're just too cowardly to admit it because it might impact whatever SLA some PM has.

It just leaves a bad taste, and the second a competitor comes along that has an acceptable offering, then I'll move. Just ridiculous gaslighting behavior.

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

#326

Post by hnburnsy »

I went through something similar just trying to get my NEST to work in home assistant, thanks to HA these are the well documented steps, and each step has multiple sub-steps...

  - Create and configure Cloud Project [Cloud Console]
  - Configure OAuth Consent screen [Cloud Console]
  - Configure OAuth Application Credentials [Cloud Console]
  - Create a Device Access Project [Device Access Console]
  - Enable events and Pub/Sub topic [Device Access & Cloud Console]
  - Link Google Account
It ended up that the linking would not stay persistent, a waste of $5 and many hours.

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

#327

Post by mlrtime »

hnburnsy wrote: post #326

I went through something similar just trying to get my NEST to work in home assistant, thanks to HA these are the well documented steps, and each step has multiple sub-steps... - Create and configure Cloud Project [Cloud Console] - Configure OAuth Consent screen [Cloud Console] - Configure OAuth Application Credentials [Cloud Console] - Create a Device Access Project [Device Access Console] - Enable events and Pub/Su…

This is a good reason to pay for the nabu casa subscription, it is worth it!

(Not for nest only, just remote access)

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

#328

Post by g-unit33 »

wosat wrote: post #166
g-unit33 wrote: post #87

Wait until the 429 error message

What's really fun is how inconsistent they are with "request" limits, at least with the embedding API. The documentation says "X requests per minute" but what they really mean is "X documents per minute". But their reporting shows requests per minute. So if you are embedding multiple documents per request, you will start getting 429s but the usage dashboard will look like you are nowhere near the limit. Super fun.

It's soo bad haha I think they just put the request limit to give comfort but it's not accurate at all

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

#329

Post by marqueewinq »

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…

What stack are you using?

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

#330

Post by Mashimo »

baobun wrote: post #301
deificx wrote: post #243

Earlier quoted context omitted.

Not GP, but I guess I'm using the same app. You guess (and then it gives you the price up front). 10 minutes before it expires it asks you if you want to extend it. There might also have been a detect if you drive away and stop feature (don't recall). Mostly these days all paid parking has registration camera's, and it just starts and stops parking for you automatically. However, there are like 3 or so apps that comp…

There is no way this is not a degradation compared to a physical meter accepting cash plus whatever. My country doesn't really have parking apps yet here and paying for parking is never a friction.

> There is no way this is not a degradation compared to a physical meter accepting cash plus whatever.

Well you can extend the parking time while not at your car. That is a big plus.

Post reply on HN