[HN Gopher] Getting a Gemini API key is an exercise in frustration
       ___________________________________________________________________
        
       Getting a Gemini API key is an exercise in frustration
        
       Author : speckx
       Score  : 792 points
       Date   : 2025-12-10 20:29 UTC (1 days ago)
        
 (HTM) web link (ankursethi.com)
 (TXT) w3m dump (ankursethi.com)
        
       | athrowaway3z wrote:
       | I didn't even need to read the article to upvote, and doing so
       | just confirmed my assumption that somebody finally wrote down
       | their frustration with Gemini.
       | 
       | My fucking god, how has Google not flagged the failure of
       | onboarding devs like Claude / Codex?
       | 
       | 3 days ago I was literally thinking, I want to throw 20$ to try
       | out Gemini alongside my Claude and Codex subs.
       | 
       | It took me a few minutes to realize its just not worth my time to
       | figure out how.
        
         | mox1 wrote:
         | I wanted to try Googles Image generation models, to compliment
         | my Claude API sub.
         | 
         | Holy Crap, I got about 45 minutes into setting up billing and
         | just gave up and un-did everything.
         | 
         | Hint: If you want to put a spending Limit on your google cloud
         | account, its not trivial.
         | 
         | I will say that Stability AI is similar to Claude, they will
         | just let you buy credits and hit an API.
        
           | madiele wrote:
           | Had the same problem, wanted to use gemini but wanted to
           | setup a speeding limit, turns out Google would prefer you to
           | risk bankruptcy for a mistake, no spending limit available
           | from what I understood, ended up going with openrouter and
           | using gemini through them instead
        
       | h02 wrote:
       | Just wait until you find out that Tier 1 only gives you up to 250
       | requests a day, and if you want more than that you'll have had to
       | have spent over $250 in Google Cloud spend, and your first
       | payment has to be more than 30 days ago. I was going to build my
       | side project using Gemini 3 Pro, but gave up after that.
        
       | nikanj wrote:
       | This reminds me of the "I just want to serve 5 terabytes" thing
       | 
       | Google does not want your money, they don't know how to count so
       | low
        
         | kevindamm wrote:
         | Broccoli Man! classic
         | 
         | https://youtu.be/3t6L-FlfeaI (2010)
         | 
         | To be fair, a lot of this changed after that video became a
         | meme.. but I'd bet that the broccoli man template is still
         | trending on memegen
        
           | vessenes wrote:
           | And the remaster! https://mbleigh.dev/posts/broccoli-man-
           | remastered/
        
             | CamperBob2 wrote:
             | Hey man, nice slop! (No, really, that's great.)
        
       | notepad0x90 wrote:
       | I think they're just too focused on enterprise billing. Someone
       | at google doesn't get that individuals trying it out is how they
       | go their work and recommend this stuff.
       | 
       | Googlers tend to exist in an isolated bubble. In the corporate
       | world, Azure is the default and they have Azure OpenAI. Why would
       | someone bother with Gemini? Unless the devs at companies have a
       | good experience with it of course.
       | 
       | Googlers are awesome/mean well, if only enough of them lurked
       | here :)
        
         | marcuskaz wrote:
         | Developer experience matters. This is what Vercel figured out
         | and why their admin screens are sooooooo much better than
         | anything AWS or Google creates.
        
           | 9rx wrote:
           | "Developer experience matters" and "Vercel" being the example
           | is something I never thought I would see together.
           | 
           | I actually do agree that Vercel's admin screens are quite
           | good compared to the other usual suspects. But I don't
           | consider that to be on the development side of things. It's
           | done decently well because it is geared towards the business
           | folks who are paying the bills.
           | 
           | Developers writing code on top of the development solutions
           | produced by Vercel have been completely forsaken.
        
             | marcuskaz wrote:
             | :thinking-face:
             | 
             | - How builds and deploys are configured
             | 
             | - The simple aspect of connecting a GitHub repo and you get
             | auto deploys
             | 
             | - Auto creating branch environments that make testing as
             | easy as a new link
             | 
             | - Just configuring users and permissions and not seeing IAM
             | anywhere is a huge win
             | 
             | My billing admins don't do any of this stuff.
        
               | 9rx wrote:
               | None of those are development tasks. IT tasks, I'd buy,
               | but anyone deeply entrenched in IT are more likely going
               | to want more powerful tools (even if harder to use).
               | Vercel is geared towards the small groups where there are
               | some developers on staff, but the budget makers are
               | playing double-duty in IT roles.
        
       | Havoc wrote:
       | Yeah can't figure out WTH is going on in google's AI ecosystem
       | either.
       | 
       | They absolutely deserve credit for their free tier API keys
       | though. That's unheard of in big cloud - an actual you can't
       | shoot yourself in the foot with a life ruining bill thing. Can't
       | recall what part of their product maze I got it from but it seems
       | to do what it says on tin
        
         | BoorishBears wrote:
         | You can sum it up as: Gemini from AI Studio and Gemini from
         | Vertex AI Studio have independent rate limits.
         | 
         | -
         | 
         | And I guess to add some context, it's because Google seemingly
         | realized that Google Cloud moves so glacially slow, and has so
         | much baggage, that they could no longer compete with scrappier
         | startups like OpenAI and Anthropic on developer mindshare.
         | 
         | So there's a separate product org that owns AI Studio, which
         | tries to be more nimble, and probably 50x'd Gemini adoption by
         | using API Keys instead of Service Accounts and JSON certs that
         | take mapping out the 9th circle of hell to deploy in some
         | environments. (although iirc Vertex now has those)
         | 
         | They definitely do ship faster than Google Cloud, but their
         | offerings actually end up feeling like a product team with
         | fewer resources than OpenAI or Anthropic (like shipping purple
         | tailwind-slop UIs as real features), which is just nuts.
        
         | impure wrote:
         | The free tier is good but they've been cracking down on rate
         | limits. Just recently they significantly dropped the max
         | requests per day.
        
       | tigranbs wrote:
       | Yeah, then try adding more quotas to scale your usage; you will
       | feel the pain! But, to be fair, it is way easier than the AWS
       | Bedrock or Microsoft Azure!
        
         | cj wrote:
         | Isn't OpenAI equally annoying?
         | 
         | I remember multiple waiting periods, and multiple requirements
         | to cross spend thresholds to increase in tiers. I remember at
         | one point spamming the OpenAI API with garbage just to consume
         | credits in order to get to the next tier to increase rate
         | limits.
         | 
         | More recently (couple months ago) I tried using a 3rd party
         | client for ChatGPT which needed a OpenAI API key. I gave up
         | after 20 mins.
        
           | ipaddr wrote:
           | The OpenAI api key generation was simple and using it no
           | problem. No different from stripe.
           | 
           | The limits are annoying.
        
         | arielcostas wrote:
         | I'd say Bedrock is the easiest since you just log into your AWS
         | account, get an AWS credential in the same way you would for
         | any other service (if you're on EC2 it's even easier) and call
         | the endpoints from the SDK. Azure though...
        
         | semi-extrinsic wrote:
         | I recently had the distinct displeasure of being the first to
         | set up a service in Azure on a new tenant at Microsoft.
         | 
         | Of course I first had to faff about adding the company credit
         | card, which took five tries and two days. Then I found I had to
         | create the appropriate resource group, before I could set up a
         | service. Fair enough, it might make sense later to have costs
         | divided up like that. After I got the resource group, I then
         | thought to start simple and spin up a single VM.
         | 
         | This gave me an error message saying that my request exceeded
         | the quota. Which quota? The built-in copilot in Azure chewed on
         | the raw error in its JSONness, and helpfully told me I could
         | find the Azure quota page by searching for it in the Azure
         | portal.
         | 
         | Once I entered the quota page, I was greeted with a message
         | saying that I was now in the new quota experience in public
         | preview mode. After many clicks I found the appropriate line
         | for the desired VM SKU in the desired region, where it said I
         | had used 0 of the quota of 30. So why didn't it work? I tried
         | to request an increased quota, just in case. That process spent
         | five minutes on "please wait", then failed with a generic error
         | message.
         | 
         | At that point I started googling around, and eventually in some
         | forum thread I found the missing piece: my resource group did
         | not yet have a subscription. After more faffing about, I got a
         | subscription associated with my resource group. What is a
         | subscription, you ask, and what is the relation between a
         | tenant, a subscription and a resource group? I haven't the
         | foggiest, but I've clicked enough buttons to make the errors go
         | away. Por ahora.
        
       | aerhardt wrote:
       | I had to warm up a Gemini API project worth a few thousand hours
       | during weeks so that I could get to the tier that allowed me to
       | carry out the workload.
       | 
       | How can you have any tokens if you haven't finished your tokens?!
        
         | throwup238 wrote:
         | _> How can you have any tokens if you haven't finished your
         | tokens?!_
         | 
         | Another rate limit in the wall.
        
           | SamvitJ wrote:
           | Clever :)
        
       | dannyobrien wrote:
       | 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 the same treatment as more
       | faceless, distant big businesses.
       | 
       | I have a friend that says Google's decline came when they bought
       | DoubleClick in 2008 and suffered a reverse-takeover: their
       | customers shifted from being Internet users and became other,
       | matchingly-sized corporations.
        
         | Sevii wrote:
         | That has definitely changed. Google AdWords today is one of the
         | most unfriendly services to onboard I've ever encountered.
         | Signing up is trivial, setting up your first ad is easy, then
         | you instantly get banned. Appeals do nothing. You essentially
         | have to hire a professional just to use it.
        
           | fersarr wrote:
           | My attempts always had validation issues that stopped the ads
           | from running but I never figured it out and stopped trying
        
           | binsquare wrote:
           | Also adding onto this, it is impossible to get human support!
           | 
           | One of my co-workers left with an active account and active
           | card but no passwords noted. The company gave up and just had
           | to cancel + create a new account for the next adwords
           | specialist.
        
           | LiamPowell wrote:
           | Yet it's still absolutely inundated with scams and
           | occasionally links that directly download malware[1] that
           | they don't action reports on. I don't think the process needs
           | to be easier if they already can't keep up with moderation.
           | 
           | [1]: https://adstransparency.google.com/advertiser/AR12938769
           | 5568...
        
             | Workaccount2 wrote:
             | It might seem vindictive, but these are the ads that google
             | shows people who block all of Googles tracking or are
             | new/blank profiles. Hear me out...
             | 
             | When Google has a bad/empty profile of you, advertisers
             | don't bid on you, so it goes to the bottom feeders. Average
             | (typically tech illiterate) people wandering through the
             | internet mostly get ads for Tide, Chevy, and [big brand],
             | because they pay Google much more for those well profiled
             | users. These scam advertisers really don't pay much, but
             | are willing to be shown to mostly anyone. They are a bit
             | like the advertiser of last resort.
             | 
             | All of that is to say, if you are getting malware/scam ads
             | from Google, it's probably because (ironically) you know
             | what you are doing.
        
           | dekhn wrote:
           | The thing to understand about google services is that they
           | see so much spam and abuse that it's easier for them to just
           | assume you are a spammer rather than a legitimate customer,
           | unless you go through other channels to establish yourself.
        
           | josefresco wrote:
           | I sell managed Google Ads services and have never had issues
           | with my clients being banned. Google Ads sucks for 1000 other
           | reasons.
        
         | cortesoft wrote:
         | 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 to someone before I can buy.
        
           | sh34r wrote:
           | > 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
           | 
           | You say that as if it isn't the entire reason why these
           | interactions should be avoided at all costs. Dynamic pricing
           | should be a crime.
        
             | pooper wrote:
             | > You say that as if it isn't the entire reason why these
             | interactions should be avoided at all costs. Dynamic
             | pricing should be a crime.
             | 
             | Does segmentation also count as dynamic pricing?
             | 
             | --                   The IT guy at Podunk Lutheran College
             | has no money: Gratis.         The IT guy at a medium-sized
             | real estate agency has some money: $500.         The IT guy
             | at a Fortune 100 company has tons of money: $50,000.
             | 
             | https://blog.codinghorror.com/oh-you-wanted-awesome-
             | edition/
        
               | transcriptase wrote:
               | The entire lab supply industry is disgusting in this
               | respect. The funding (and recent grants) that a given
               | professor or research lab has is generally publicly
               | available information that vendors will buy in easily
               | digestible formats from brokers and companies that scrape
               | the websites of major granting agencies.
               | 
               | All of their products, however realistically
               | commoditized, will require a drawn out engagement with a
               | rep who knows how much money you've received recently and
               | even has an outline what research you plan to do over the
               | next few years since even the detailed applications often
               | get published alongside funding allocations.
               | 
               | The exact same piece of equipment, consumables required
               | to use it, and service agreements might be anywhere from
               | X to 10X depending on what they (as a result of
               | asymmetrically available knowledge) know you need and how
               | much you could theoretically spend.
        
               | lokar wrote:
               | A group of research universities should start a non-
               | profit co-op to produce this for them.
               | 
               | Getting just the university of California should be
               | enough critical mass.
        
               | xmcqdpt2 wrote:
               | Depends on the product. Some products just have a single
               | supplier for the whole world over, because they are
               | extremely specialized.
               | 
               | It's not uncommon though for eg departments to have
               | common equipment that they negotiate together.
        
               | Terr_ wrote:
               | Not parent poster, but I think a more practical approach
               | is to ban _secret_ discriminatory pricing.
               | 
               | If everybody can see the prices that would be quoted in
               | other circumstances, that exerts a strong moderating
               | force against abuse.
               | 
               | It won't help you if there's a monopoly, but I consider
               | that a separate problem needing separate solutions.
        
             | xboxnolifes wrote:
             | Pricing tiers are a form of dynamic pricing. Service free
             | tiers basically couldn't exist without dynamic pricing, as
             | they are subsidized by the paying tiers.
        
             | nicbou wrote:
             | Certain purchases (like health insurance in my country)
             | should be a conversation, because the options are
             | fiendishly complex and the attributes people typically use
             | for comparison are wrong. The consequences are lifelong.
        
               | Hendrikto wrote:
               | But not a conversation to a sales rep who will just push
               | whatever gives them the largest commission.
        
               | sceptic123 wrote:
               | I thought thees things were complex on purpose to make it
               | hard for people to easily understand and compare so you
               | have to speak to a sales person who can do the upselling
        
               | nicbou wrote:
               | 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.
        
               | sceptic123 wrote:
               | 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.
        
               | cortesoft wrote:
               | Every time I go to a presentation about the health care
               | options I have, it ends up just being the representative
               | reading off a slide with the actual information. All the
               | information I need is in print. I have never received a
               | single piece of valuable information that wasn't easier
               | to get just reading the docs myself.
        
           | AznHisoka wrote:
           | You are also a developer though, and developers are notorious
           | for wanting self serve.
           | 
           | Someone who works in finance or conpliances might want a
           | demo, or views those things as signals the product is for
           | serious use cases.
        
             | dpkirchner wrote:
             | Sure, and they should have that option. But in my
             | experience business-folks ask techies to evaluate services
             | all the time, and ideally we can just start out in the
             | low-/no-touch tier to feel things out. If that tier isn't
             | available, us techs might just try a different service.
        
               | timr wrote:
               | The kind of products hidden behind sales calls are
               | generally the sort where the opinion of IC-level tech
               | staff is next to irrelevant. With these kinds of
               | products, the purchase decision is being made at a group
               | level, the contract sizes are large, and budgetary
               | approvals are required. It's a snowball the size of a
               | house, and it started rolling down the mountain months
               | (or years) before it got to your desk. Literally nobody
               | cares if you buy a single license or not, and if you
               | (personally) refuse to try it because it doesn't have
               | self-service, you'll be ignored for being the bad
               | stereotype of an "engineer", or worse.
               | 
               | About the only time you'll be asked to evaluate such a
               | product as an IC is when someone wants an opinion about
               | API support or something equivalent. And if you refuse to
               | do it, the decision-makers will just find the next guy
               | down the hall who won't be so cranky.
        
               | TheTaytay wrote:
               | I think this is true at larger organizations, but even a
               | "small/medium" startup can easily sign contracts for
               | single services for $100k+, and in my experience,
               | salespeople really do care about commissions at those
               | price points. A lot of software gets a foothold in an org
               | by starting with the ICs, and individuals, not groups,
               | are often the ones that request or approve software.
               | Github and Slack are good examples of services who make
               | very good use of their ability to self-serve their
               | customers out of the gate, in spite of also supporting
               | very large orgs.
               | 
               | In these conversations, I never ever see the buyers
               | justifying or requesting a sales process involving people
               | and meetings and opaque pricing.
               | 
               | It's true that complicated software needs more talking,
               | but there is a LOT of software that could be bought
               | without a meeting. The sales department won't stand for
               | it though.
        
               | timr wrote:
               | > A lot of software gets a foothold in an org by starting
               | with the ICs, and individuals, not groups, are often the
               | ones that request or approve software.
               | 
               | Not really. Even if we keep the conversation in the realm
               | of startups (which are not representative of anything
               | other than chaos), ICs have essentially no ability to
               | take unilateral financial risk. The Github "direct to
               | developer" sales model worked for Github at that place
               | and time, but even they make most of their money on
               | custom contracts now.
               | 
               | You're basically picking the (very) few services that are
               | most likely to be acquired directly by end users. Slack
               | is like an org-wide bike-shedding exercise, and Github is
               | a developer tool. But once the org gets big enough, the
               | contracts are all mediated by sales.
               | 
               | Outside of these few examples, SaaS software is almost
               | universally sold to non-technical business leaders.
               | Engineers have this weird, massive blind spot for the
               | importance of sales, even if their own paycheck depends
               | on it.
        
               | cortesoft wrote:
               | This is really not true in my experience. In fact, all my
               | experience has been with products that aren't THAT
               | expensive, and the individual dev teams do decide. These
               | are SaaS products, and sometimes the total cost is under
               | $1000 a year, and I still can't get prices without
               | contacting sales.
               | 
               | Also, it isn't just ICs. I have worked as a senior
               | director, with a few dozen people reporting into me...
               | and I still never want to talk to a sales person on the
               | phone about a product. I want to be able to read the
               | docs, try it out myself, maybe sign up for a small plan.
               | Look, if you want to put the extras (support contracts,
               | bulk discounts, contracting help, etc) behind a sales
               | call, fine. But I need to be able to use your product at
               | a basic level before I would ever do a sales call.
        
           | Workaccount2 wrote:
           | The number one rule of business that should just be passively
           | reiterated to everyone working in any type of transactional
           | field:
           | 
           | 1. Never make it hard for people to give you money.
        
             | the_snooze wrote:
             | Parking apps don't seem to care much for that. They know
             | you'll jump through their shoddy UIs and data collection
             | because they have a local monopoly. Often with physical
             | payment kiosks removed and replaced with "download our
             | shitty app!" notices.
        
               | Workaccount2 wrote:
               | Plenty of people on here looking to disrupt a market with
               | tech...c'mon guys, get on it
               | 
               | Edit: On second thought, there is a perverse incentive at
               | work (and probably one of the "lowest friction" ways to
               | get money), which is issuing government enforced fines.
        
               | wlesieutre wrote:
               | The crappy apps that replaced parking meters _are_ the
               | people who disrupted the existing market with tech
        
               | prasadjoglekar wrote:
               | There's also the unfortunate stick of a much larger
               | parking ticket that is even more trouble to contest.
        
               | CamperBob2 wrote:
               | (Shrug) No, I'll just park someplace else. I probably
               | need a good walk anyway.
               | 
               | There's no such thing as a monopoly when it comes to
               | parking. If there is -- if every single parking spot
               | within walking distance is locked behind a shitty app --
               | then you need to spend some quality time at your next
               | city council meeting making yourself a royal PIA.
        
               | cyberax wrote:
               | LOL. All the city parking spots around here are managed
               | by PayByPhone, and pretty much all private parking spots
               | are DiamondParking paid through ParkMobile.
               | 
               | I raised the issue with my local city council rep. She
               | didn't care.
        
               | vel0city wrote:
               | You should read about the Chicago Parking Meters scandal.
               | The City of Chicago leased all their meter rights to a
               | private corporation on a 75 year lease for a bit over a
               | billion dollars. The private company made it back in the
               | first decade. The city even has to pay the parking
               | company when they have to do construction or throw events
               | that blocks the parking as revenue compensation.
               | 
               | https://en.wikipedia.org/wiki/Chicago_Parking_Meters
               | 
               | This doesn't apply to private pay lots though, so there's
               | still _some_ amount of  "choice".
        
               | harikb wrote:
               | Sometimes I think, it should be illegal for these
               | government contracts to last beyond 5 years for exactly
               | this reason. Who know what kind of deals are being made.
               | Some administration could sign away the whole country on
               | their last day.
        
               | specproc wrote:
               | It's straight up corruption, pure and simple. The UK is
               | also full of this crap. The officials and executives
               | who've facilitated and profited from this robbery should
               | be jailed.
        
               | jacquesm wrote:
               | So, the officials that signed that deal went to jail,
               | right?
        
               | 542354234235 wrote:
               | I don't think a monopoly requires literally every
               | possible option to be controlled by the monopolistic
               | entity.
               | 
               | Also, I only have time for so many hills on which to die.
               | I'm not sure parking reform, while worthy, makes the cut.
        
               | StilesCrisis wrote:
               | They get paid more if you get a parking ticket.
        
               | petesergeant wrote:
               | The RyanAir model of technically legal, but actively
               | playing a zero-sum game against their consumers'
               | diligence.
        
               | deinonychus wrote:
               | i'm currently disputing a bill with a parking company.
               | there's a kiosk at the movie theater served by the
               | parking lot, so that you can get free parking if you see
               | a movie. the kiosk has an option for you to describe your
               | car if you forgot your license plate number. i did that
               | and they sent me a bill for unpaid parking.
               | 
               | customer service is unable to acknowledge why that
               | feature is offered and can only assert that if you park
               | you gotta pay. after threatening to complain to the BBB
               | and my state AG they have graciously offered to drop the
               | ticket to $25.
               | 
               | thank you for listening to me vent :)
        
               | Mashimo wrote:
               | Huh, where I live you often can use many different
               | parking apps, and the one i tried is very simple and user
               | friendly.
               | 
               | Start app, wait for gps, turn time wheel, press start.
        
               | edwinjm wrote:
               | Turn time wheel? How do you know in advance how long you
               | stay? Where I live, you start and when you leave, you
               | click stop. You also get reminders in case you forgot to
               | stop.
        
               | deificx wrote:
               | 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
               | compete here so you need a profile with all of them for
               | this to work and you also need to enable this on all the
               | apps.
        
               | baobun wrote:
               | 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.
        
               | dbspin wrote:
               | At least in my country they face no competition. For a
               | given location, only one app will work.
        
           | brightball wrote:
           | It depends on the environment.
           | 
           | If a platform is designed in a way that users can sign up and
           | go, it can work well.
           | 
           | If an application is complicated or it's a tool that the
           | whole business runs on, often times the company will discover
           | their customers have more success with training and a point
           | of contact/account manager to help with onboarding.
        
           | satvikpendem wrote:
           | You're not the target customer.
        
           | Arainach wrote:
           | Instant self signup died with cryptocurrency and now AI: any
           | "free" source of compute/storage/resources will be
           | immediately abused until you put massive gates on account
           | creation.
        
             | kijin wrote:
             | Who said anything about free? OP wanted to pay Google $100.
        
               | Arainach wrote:
               | OP wanted "instant self signup". That doesn't work when
               | malicious actors are trying to register accounts with
               | stolen credentials. The verification flow is required
               | because of the amount of pressure from malicious actors
               | against both free and newly-created accounts.
               | 
               | "Give access now, cancel if validation fails" doesn't
               | work either - so long as attackers can extract more than
               | 0 value in that duration they'll flood you with bad
               | accounts.
        
               | kijin wrote:
               | Well, then give me self-signup with a clearly outlined
               | verification flow that I can follow from A to Z.
               | 
               | If you give me a form where I can upload my passport or
               | enter a random number from a charge on my card, that
               | counts as "instant" enough. On the other hand, if you
               | really need to make me wait several days while you
               | manually review my info, fine, just tell me upfront so I
               | can stop wasting my time. And be consistent in your UI as
               | to whether I'm verified yet. It's all about managing
               | expectations.
               | 
               | Besides, Amazon hands out reasonable quotas to newly
               | created accounts without much hassle, and they seem to be
               | doing okay. I won't believe for a second that trillion-
               | dollar companies like Google don't know how to keep abuse
               | at a manageable level without making people run in
               | circles.
        
           | makeitdouble wrote:
           | > sales people
           | 
           | > talk to people
           | 
           | There will clearly be a gap in understanding, when their
           | whole job is to talk to people, and you come to them to argue
           | for clients to not do that.
           | 
           | As you point out it's not that black and white, most
           | companies will have tiers of client they want to spend less
           | or more time with etc. but sales wanting direct contact with
           | clients is I think a fundamental bit.
        
             | Hendrikto wrote:
             | > sales wanting direct contact with clients
             | 
             | But what do the clients want? Your business should not be
             | structured to make sales people happy.
        
           | arjie wrote:
           | That's just a disqualification process. Many products don't
           | want a <$40k/annual customer because they're a net drain. For
           | those, "talk to sales" is a way to qualify whether you're
           | worth it as a customer. Very common in B2B and makes sense.
           | Depends entirely on the product, of course.
        
           | biglyburrito wrote:
           | My previous company was like this, and it boggles the mind.
           | 
           | Sales is so focused on their experience that they completely
           | discount what the customer wants. Senior management wants
           | what's best for sales & the bottom line, so they go along
           | with it. Meanwhile, as a prospective customer I would never
           | spend a minute evaluating our product if it means having to
           | call sales to get a demo & a price quote.
           | 
           | My team was focused on an effort to implement self-service
           | onboarding -- that is, allowing users to demo our SaaS
           | product (with various limitations in place) & buy it (if so
           | desired) without the involvement in sales. We made a lot of
           | progress in the year that I was there, but ultimately our
           | team got shutdown & the company was ready to revert back to
           | sales-led onboarding. Last I heard, the CEO "left" & 25% of
           | the company was laid off; teams had been "pivoting" every
           | which way in the year since I'd been let go, as senior
           | management tried to figure out what might help them get more
           | traction in their market.
        
             | eitally wrote:
             | My current employer offers three tiers of licensing with
             | clearly articulated prices & benefits (the lowest of which
             | is free), but also offers a "Custom - let's talk" option
             | because the reality is that sometimes customer situations
             | are complicated and bespoke contracts make sense, but at
             | least the published pricing provides directional guidance
             | heading into a discussion. I think this is reasonable.
        
           | SecretDreams wrote:
           | > use their sales skills
           | 
           | Boy oh boy are they going to be surprised when they learn
           | what AI can replace.
        
           | pmontra wrote:
           | If it's only pay and go why have Sales at all? At the very
           | best you need only a slimmed down Sales Department, so being
           | against pay and go is self preservation.
        
             | hrimfaxi wrote:
             | For enterprise deals.
        
       | nl wrote:
       | You literally cannot buy Antigravity with a non-personal Google
       | account.
       | 
       | I read someone on here who is using Gemini via OpenRouter because
       | it was the only way they could pay for it.
        
         | verdverm wrote:
         | I'm using it fine through both aistudio and vertex ai, direct
         | API calls
         | 
         | It's not at all hard generally, the core of this issue is
         | centered around gemini-cli which is a hot pile of trash. The
         | inability to get keys or account credentials (like why even use
         | an API key, Google is top notch in auto-auth/WIF)
         | 
         | Insanity to me how gemini-cli is so bad at the basics with so
         | many great Google packages in open source that handle all this
         | transparently. All I need to do is have my gcloud authd with
         | the right account/project. I sarcastically assume his is
         | because they vibe coded gemini-cli and it implemented
         | everything from scratch, missing out on reusing those great
         | packages
        
           | nl wrote:
           | > I'm using it
           | 
           | Do you mean Antigravity or Gemini?
           | 
           | If you mean Antigravity then.. how? Their docs say you can't
           | do this.
           | 
           | If you mean Gemini then I personally haven't had issues but
           | haven't tried to productionize a Gemini app. The OPs account
           | seems to reflect other comments here.
        
             | verdverm wrote:
             | I already said how I'm calling Gemini
             | 
             | > direct API Calls
             | 
             | I suspect Antigravity to be a big flop like gemini-cli.
             | They are so bad in this area they couldn't even write an
             | extension or fork oss-code, instead spending $2B to pork an
             | open source project with someone else's branding
        
       | axi0m wrote:
       | Gosh, this story resonates so much with me... I had the exact
       | same experience few days ago, desperately trying to get a small
       | agent prototype working for a quick demo. I spent an good hour
       | dealing with that pile of nonsense. Online payments and accounts
       | management have been mastered for 20 years now, why do we still
       | have to endure such things? It just kills me. The same goes with
       | Azure (and all MS online-related services), if not even worse.
        
       | modeless wrote:
       | Seems like the real problem is something about his account or
       | credit card tripped some fraud detectors and he got stuck in a
       | part of the system designed to prevent credit card fraud rather
       | than facilitate legitimate use. I can certainly imagine that
       | Google gets a lot of chargebacks from people who had their credit
       | card numbers stolen to mine bitcoin or whatever on Google Cloud.
        
         | jwrallie wrote:
         | Having moved from one country to another, I tripped all kinda
         | of anti fraud systems and the only way out was to share my ID
         | with every other company. It's annoying but one common thing is
         | that anti fraud systems seem to require humans in the loop, so
         | it's better to give up and get back to it next day.
         | 
         | The most annoying company I dealt with was Blizzard. I just
         | wanted to play a game but it took days of back and forth,
         | meanwhile I started to play something else and lost interest.
        
       | rtaylorgarlock wrote:
       | Interesting perspective. I've mainly felt like i have 'American
       | privilege' regarding the ease with which i open accounts of
       | basically any sort on a whim, usually with little friction.
        
         | mrj wrote:
         | Oh no, this is just a Google thing. I've done the same
         | verification bs for four different companies now, multiple
         | times for each of them. I just keep an image of my license on
         | my computer so I can upload it on demand. Google's payment
         | verification is byzantine.
         | 
         | It'll trigger when you sign up.
         | 
         | It'll trigger if you create an Android developer account.
         | 
         | It'll trigger if you get a new phone.
         | 
         | It'll trigger if your card expires.
         | 
         | It'll trigger the _month before your card expires_. Why? Fuck
         | you, that 's why.
        
       | neom wrote:
       | 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 complex within a
       | massive machine - given how focused on the product he appears to
       | be, I have high hopes.
       | 
       | https://x.com/OfficialLoganK
        
         | verdverm wrote:
         | 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 started their own companies
        
         | mvkel wrote:
         | 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.
        
           | magicalhippo wrote:
           | 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.
        
       | gxs wrote:
       | This is a longstanding issue we've had, not just with Gemini
       | 
       | Even with something as simple as google workspace - permissioning
       | service accounts and authentication are a pain in the ass
       | 
       | The docs suck and of course there's no one to help
        
       | sirfz wrote:
       | I find GCP frustrating (coming from AWS) but luckily asking
       | Gemini how to do things makes it much easier.
        
       | consumer451 wrote:
       | Wasn't this type of Google thing clearly called out in the
       | Karpathy Software 3.0 talk?
       | 
       | It's interesting to me this UX problem is not readily solved.
       | 
       | What is the sticking point in a big org? I don't have a point of
       | reference.
        
         | chillfox wrote:
         | It will be politics, it's always politics. Large orgs works a
         | lot like the feudal system.
        
           | consumer451 wrote:
           | I would like to think that this is why higher level execs get
           | paid the truly big bucks... to cut through all of that.
           | 
           | Otherwise, this sounds a lot like "impenetrable government
           | bureaucracy." I thought business was supposed to be better.
        
       | niwtsol wrote:
       | The article lightly mentions it, but how AWS and Google Cloud
       | Console are so absolute nonsensical in UX and ease of use is
       | beyond comprehension.
        
         | polalavik wrote:
         | 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 can make money
         | (from people like me) because they just circumvent the bullshit
         | or wrap the dogshit experience (aws) into a much better
         | experience. bless supabase.
        
           | herpdyderp wrote:
           | DigitalOcean is such a dream to use. I also really appreciate
           | all their guides for almost everything web server related.
        
             | sbrother wrote:
             | How is their managed Kubernetes product nowadays? I've
             | realized all I really use on GCP and AWS is managed
             | Kubernetes and Postgres, and I feel like I must be
             | overpaying particularly for GPU instances.
        
           | TheTaytay wrote:
           | 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 accounts. Multiple.
           | That's not a brag. That's an admonition.
           | 
           | Digital Ocean, Hetzner, Render, etc, seem to have figured out
           | how to rent millions of dollars of computers and services out
           | every month without requiring you to become "certified" on
           | their platform.
        
             | polalavik wrote:
             | This 1000%. The Ui is so convoluted I'm scared that I'll
             | leave something on and be charged a fortune.
        
         | sofixa wrote:
         | Baring them using specific marketing terms (so you have EC2 for
         | what are basically virtual machines), for which both the docs
         | and the portal itself provide helpful information, what do you
         | mean? I find GCP's console and whole set up to be slightly
         | better, but both it and AWS are fine.
         | 
         | Now Azure, or anything made by VMware, you just know they hate
         | you.
        
           | jiggawatts wrote:
           | I love how people think Azure is somehow worse than AWS when
           | the latter isn't even a single portal, it's _many_ , each of
           | which shows just one product in one region. Oh, you needed a
           | VM with a network and some storage, including access to blobs
           | somewhere else in the world? Just open up a dozen tabs and
           | join the randomly generated gibberish resource identifiers
           | yourself manually like a savage!
        
             | doganugurlu wrote:
             | Exactly. Just as the lord intended.
             | 
             | Although Azure just randomly fails, and then it turns out
             | it actually worked but the UI had failed. But then the next
             | step throws an obscure error message, but you get around
             | that on a different screen, so on so forth...
        
             | sofixa wrote:
             | > I love how people think Azure is somehow worse than AWS
             | when the latter isn't even a single portal, it's many, each
             | of which shows just one product in one region
             | 
             | Yep, which means that even an entire AWS region being down
             | has no impact on anything else. Unlike Azure where a single
             | DC in Texas being out meant no auth for anyone, anywhere in
             | the world.
             | 
             | And aren't Azure and O365 infamous for having a convoluted
             | web or multiple portals to such an extent that there are
             | multiple websites trying to help you navigate them with
             | direct links?
             | 
             | And in any case, Azure is not a serious cloud provider and
             | anyone picking it is at best not paying attention, at worst
             | negligent at their job (yeah I know, Azure is the cloud
             | your bosses' boss picks after some golfing and a nice
             | dinner). They have a ~quarterly critical, trivial to
             | exploit, usually cross-tenant, vulnerability. Often with
             | Microsoft having no mitigation and having the the faintest
             | idea if it was exploited. And stalling the security
             | researchers for weeks if not months.
             | 
             | The security posture of Azure is so appalling it's clear
             | nobody at that org who has any power cares about security
             | in the slightest. And it has been obvious for a few years
             | now. Search Wiz's blog just for their collection of ~10
             | Azure CVEs. For the latest horrific one, cf:
             | https://www.cve.org/CVERecord?id=CVE-2025-55241
        
           | niwtsol wrote:
           | I agree that Google's console is slightly better, but a few
           | of my gripes with AWS specifically: 1. input fields that lack
           | basic validation so you do some action and then get an error
           | message that is cryptic when simple "if this value selected
           | in drop down, you can't do X". Another example of this is
           | needing to get quota increase for your AWS account for an
           | instance type, but nothing on the frontend tells you that,
           | and you have to go through 3 or 4 weirdly linked support
           | ticket/pages to figure out how to make a request for an
           | instance. 2. As another commenter said, billing - so many
           | pages and ways to cut the data but somehow it still seems
           | complicated to find "which instance is attached to resource X
           | that is costing me $Y per month" 3. Documentation not
           | matching UI - so many PMs/TPMs over the years making
           | resources that you find a blog/post that is a walk through,
           | but then you find they redesigned or moved a button and that
           | makes it difficult to follow. 4. I worked at Amazon for a bit
           | and the internal tools feel like they were built in the early
           | 2000s and I think I have PTSD from that which I still ascribe
           | bad feelings towards AWS as there are similarities
           | 
           | I think as you use it, you start to understand the gotchas
           | and the flows you need to do to get something working. I also
           | appreciate there is a ton of stuff they are empowering users
           | to do and the scale is incomprehensible, but just frustrated
           | the UX is so poor.
           | 
           | I just started using Azure for another project and my
           | goodness, I can't even login to that vs the microsoft ads
           | account w/ the same email because of some weird MS365
           | permissions issue - by far the worst.
        
         | heymijo wrote:
         | The really fun part was after getting billing finally set up in
         | the cloud console trying to find what model name you actually
         | have to use to call it via the API. Conflicting information?
         | Sure! Gemini cloud help being useless? Naturally.
         | 
         | Oh and don't forget that error message being returned when you
         | try to call the API is because you didn't give your project the
         | proper permissions in google cloud console. What permissions do
         | you need? -\\_(tsu)_/-
         | 
         | Google Cloud Console feels like being stuck in the seventh
         | circle of hell.
        
       | plaidfuji wrote:
       | > The "Set up billing" link kicked me out of Google AI Studio and
       | into Google Cloud Console, and my heart sank. Every time I've
       | logged into Google Cloud Console or AWS, I've wasted hours upon
       | hours reading outdated documentation, gazing in despair at graphs
       | that make no sense, going around in circles from dashboard to
       | dashboard, and feeling a strong desire to attain freedom from
       | this mortal coil.
       | 
       | 100% agree
        
       | arielcostas wrote:
       | Wait until you see Azure. Apparently you need to create either an
       | "Azure OpenAI" or a "Microsoft Foundry", where AFAIK (got an
       | email last week) Foundry now includes everything AI including
       | "Azure OpenAI", the former "Cognitive Services" (for speech,
       | computer vision and other stuff) and inference on non-OpenAI
       | models. But wait, because once you create that, you are told to
       | go to another portal (ai.azure.com) where you get an "old"
       | foundry experience and anew one that can't be enabled for every
       | project. Oh, wait, did I mention there apparently used to be a
       | "Foundry" and a "Foundry Project"? Oh, and all those apparently
       | work with a single API key, unless (I guess) you set up
       | authentication with the Azure SDK, which makes you go back to
       | Azure Portal (or maybe Entra ID?).
       | 
       | All of that while trying to explain to your non-technical boss
       | how he can browse the voices available at "the Azure thingy" to
       | pick his favourites to then pick and use in the project due
       | relatively soon. Since, of course, you told him the original
       | Cognitive Speech Services (or Speech Services, or Cognitive
       | Services-Speech, or whatever they decided to call it on that
       | specific page) semi-public URL where he could browse the gallery
       | was "speech.microsoft.com" which is now semi-dead with awful
       | loading times that seem some server issue and has been happenning
       | for a few months now. Or tell them to go to the "new foundry"
       | where he might not be able to find the resource or might not have
       | stuff in the regions you were using up until then, or whatever
       | crap this 3.56 trillion-dollar company decides to throw at you to
       | prevent you from using their services.
       | 
       | And all of this is the exploration phase, where you just use the
       | GUIs and copy things around until they work. Then you need to
       | figure out what you did (and more importantly, where) to be able
       | to write some Terraform/OpenTofu or Bicep or similars to try and
       | keep the environment replicable to avoid the excruciating pain of
       | repeating every single step you followed to get it on a working
       | state.
       | 
       | At the very least, Google was nice enough to launch Vertex AI
       | inside GCP for enterprises that have figured that out, and then
       | Google AI Studio as an almost completely separate thing that only
       | is bound to Google Cloud for billing purposes, similar to how
       | Firebase is integrated too.
        
       | obmelvin wrote:
       | I don't understand the multiple posts / comments I've seen about
       | this.
       | 
       | I google `gemini API key` and the first result* is this docs
       | page: https://ai.google.dev/gemini-api/docs/api-key
       | 
       | That docs page has a link in the first primary section on the
       | page. Sure, it could be a huge CTA, but this is a docs page, so
       | it's kinda nice that it's not gone through a marketing make over.
       | 
       | * besides sponsored result for AI Studio
       | 
       | (Maybe I misunderstood and all the complaints are about billing.
       | I don't remember having issues when I added my card to GCP in the
       | past, but maybe I did)
        
         | verdverm wrote:
         | Most of them are correlating gemini-cli experience (trash) with
         | the broader access to Gemini via studio or cloud (not at all a
         | problem)
        
           | Leynos wrote:
           | They could always just use OpenCoder, Crush or Goose with
           | OpenRouter (https://openrouter.ai/google/gemini-3-pro-
           | preview)
        
             | verdverm wrote:
             | 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
             | thinking and paid features (2) sit at the wrong level. ADK
             | gives me building blocks for generalized agents, whereas
             | most of these frameworks are tied to coding and some
             | peculiarities you see there (like forcing you to deal with
             | studio, no thanks). They also have too much abstraction and
             | I want to be able to control the lower level knobs and
             | levers
             | 
             | ADK is the closest to what I've been looking for, an analog
             | to kubernetes in the agentic space. Deal with the bs, give
             | me great abstractions and building blocks to set me free.
             | So many of the other frameworks want to box you into how
             | they do things, today, given current understanding. ADK is
             | minimal and easy to adjust as we learn things
        
               | FeepingCreature wrote:
               | openrouter just gives you prompt in, result out in
               | standard openai api format.
        
               | verdverm wrote:
               | These projects are all a level above open router, they
               | call the same standard APIs, or even custom ones and
               | manage the translation. They do a lot more as well
               | 
               | ADK has an option to use litellm (openrouter
               | alternative), among many options
               | 
               | https://google.github.io/adk-docs/agents/models/#using-
               | cloud...
        
           | amluto wrote:
           | > Gemini via studio
           | 
           | Excuse me? If you mean AI Studio, are you talking about the
           | product where you can't even switch which logged in account
           | you're using without agreeing to its terms under whatever
           | random account it selected, where the ability to turn off
           | training on your data does not obviously exist, and where
           | it's extremely unclear how an organization is supposed to pay
           | for it?
        
             | rezonant wrote:
             | Yes, much like admin.google.com (the GSuite admin
             | interface), which goes ahead and tries to two-factor your
             | personal GMail account every single time you load it
             | instead of asking you which of the actual GSuite accounts
             | you're signed into you'd like to use...
        
               | amluto wrote:
               | I love how the two factor screen has no obvious way to
               | tell it that you want a different account.
               | 
               | Hint: you can often avoid some of this mess by adding the
               | authuser=user@domain to the URL.
        
               | Marsymars wrote:
               | I long ago concluded that trying to mix multiple google
               | (or MS) accounts in the same browser profile is a path to
               | madness.
        
               | verdverm wrote:
               | seriously, just use different chrome profiles, but part
               | of the issue is that they are so interwoven you pretty
               | much have to do this
        
               | andoando wrote:
               | I always have a buggy ass hell experience with having
               | multiple google accounts pretty much across all their
               | services. I've been wondering if its just me or how the
               | hell this is normal.
        
               | verdverm wrote:
               | Yeah, with multiple chrome profiles, you have to be
               | mindful of which one you last had focused before clicking
               | a link from an external application (i.e. tailscale), so
               | that it opens the new tab in the right instance so the
               | account(s) you use in it are available
               | 
               | Def use multiple chrome profiles if you aren't. You can
               | color code them to make visual identification a breeze
        
               | rezonant wrote:
               | I'm aware of multiple Chrome profiles and I do not want
               | to use them. Google should simply make their account
               | switching consistent across their apps and work sensibly
               | in these corner cases.
        
               | verdverm wrote:
               | "simply" is doing a lot of work, profiles is the outcome
               | of addressing the problems you are talking about. Many
               | people enjoy them and find them useful. Why are you
               | against using them?
        
               | rezonant wrote:
               | Simply isn't doing much work, account switching works
               | just fine on GMail, search, maps, calendar etc. The issue
               | is that some Google apps do not follow the standard of
               | the overall fleet. Google gives us the account switching
               | feature, it's obviously an intended way to use their
               | products. Otherwise they would not give you that and tell
               | you to use browser profiles.
               | 
               | I don't want my history, bookmarks, open tabs and login
               | sessions at every website divided among my 5 GSuite
               | workspace accounts and my 1 personal Gmail. That adds a
               | bunch of hassle for what? The removal of a minor
               | annoyance when I use these specific Google apps? That is
               | taking a sledge hammer to a slightly bent nail.
               | 
               | If it works for you, great, that's why it's there. But
               | doing this for anything more than the basic happy path
               | setup of "I have one personal account and 1 GSuite work
               | account" is nuts in my opinion.
        
             | verdverm wrote:
             | Don't get me wrong, aistudio is pretty bad and full of
             | issues, but getting an apikey was not hard or an issue
             | itself. Using any auth method besides personal account
             | oauth with gemini-cli never worked for me after hours of
             | trying
        
           | arthurfirst wrote:
           | I have a claude max subscription and a gemini pro sub and I
           | exclusively use them on the cli. When I run out of claude max
           | each week I switch over to gemini and the results have been
           | pretty impressive -- I did not want to like it but credit
           | where credit is due to google.
           | 
           | Like the OP others I didn't use the API for gemini and it was
           | not obvious how to do that -- that said it's not cost
           | effective to _develop_ without a Sub vs on API pay-as-you-go,
           | so i do no know why you would? Sure you need API for any
           | applications with built-in LLM features, but not for
           | developing in the LLM assisted CLI tools.
           | 
           | I think the issue with cli tools for many is you need to be
           | competent with cli like a an actual nix user not Mac first
           | user etc. Personally I have over 30 years of daily shell use
           | and a sysadmin and developer. I started with korn and csh and
           | then every one you can think of since.
           | 
           | For me any sort of a GUI slows me down so much it's not
           | feasible. To say nothing of the physical aliments associated
           | with excessive mousing.
           | 
           | Having put approaching thousands of hours working with LLM
           | coding tools so far, for me claude-code is the best, gemini
           | is very close and might have a better interface, and codex is
           | unusable and fights me the whole time.
        
             | verdverm wrote:
             | > it's not cost effective to develop without a Sub vs on
             | API pay-as-you-go, so i do no know why you would
             | 
             | My spend is lower, so I conclude otherwise
             | 
             | > I think the issue with cli tools for many is...
             | 
             | Came from that world, vim, nvim, my dev box is remote,
             | homelab
             | 
             | The issue is not that it is a CLI, it's that you are trying
             | to develop software through the limited portal of a CLI.
             | How do you look at multiple files at the same time? How do
             | you scroll through that file
             | 
             | 1. You cannot through a tool like gemini-cli
             | 
             | 2. You are using another tool to look at files / diffs
             | 
             | 3. You aren't looking at the code and vibe coding your way
             | to future regret
             | 
             | > or me any sort of a GUI slows me down so much it's not
             | feasible.
             | 
             | vim is a "gui" (tui), vs code has keyboard shortcuts,
             | associating GUI with mouse work
             | 
             | > Having put approaching thousands of hours working with
             | LLM coding tools so far, for me claude-code is the best,
             | gemini is very close and might have a better interface, and
             | codex is unusable and fights me the whole time.
             | 
             | Anecdotal "vibe" opinions are not useful. We need to do
             | some real evals because people are telling stories like
             | they do about their stock wins, i.e. they don't tell you
             | about the losses.
             | 
             | Thousands of hours sounds like your into the vibe coding /
             | churning / outsourcing paradigm. There are better ways to
             | leverage these tools. Also, if you have 1000+ hours of LLM
             | time, how have you not gone below the prepackaged
             | experience Big AI is selling you?
        
         | politelemon wrote:
         | I did this same thing and this was my first result too. I am
         | just not seeing how the author ended up where they did, unless
         | knowing how to use Google search is not a core skill.
        
           | malfist wrote:
           | I did notice in their post instead of searching for answers,
           | they asked Gemini how to do things, and when that didn't
           | work, they asked Claude.
           | 
           | I often see coworkers offload their work of critical thinking
           | to an AI to give them answers instead doing the grunt work
           | nessecary to find their answers on their own.
        
             | dugidugout wrote:
             | This rhetoric worries me. If you insist on degrading others
             | at least fix it to something like:
             | 
             | > [They seemingly] can't think on their own without an AI
             | [moderating]
             | 
             | They _literally_ can think on their own, and they
             | _literally_ did think up a handful of prompts.
             | 
             | A more constructive way to make what I assume to be your
             | point would be highlighting why this shift is meaningful
             | and leaving the appeal to ego for yourself.
        
               | malfist wrote:
               | I agree with your assessment, I am in the wrong here.
               | It's easy to be extra judgmental to anonymous figures on
               | a blog you'll never meet. Thank you for reminding me to
               | give people the benefit of doubt and not jump to worst
               | case assumptions.
               | 
               | I've edited my post to be more charitable
        
               | ipaddr wrote:
               | There is some truth in that statement.
               | 
               | Low energy afternoons you might be able to come up with a
               | prompt but not the actual solution.
               | 
               | There are people offloading all thoughts into prompts
               | instead of doing the research themselves and some have
               | reached a point where they lost the ability to do
               | something because of over AI use.
        
           | mediaman wrote:
           | Read the full post. Partway down you will see they agree with
           | you that getting an API key is not hard.
           | 
           | Paying is hard. And it is confusing how to set it up: you
           | have to create a Vertex billing account and go through a
           | cumbersome process to then connect your AIStudio to it and
           | bring over a "project" which then disconnects all the time
           | and which you have to re-select to use Nano Banana Pro or
           | Gemini 3. It's a very bad process.
           | 
           | It's easy to miss this because they are very generous with
           | the free tier, but Gemini 3 is not free.
        
         | leopoldj wrote:
         | As the article states, generating the key itself is easy. But
         | getting credit and billing are the issues.
        
           | knollimar wrote:
           | I have it running and calling but it's not showing the usage
           | and I set it up the day gemini 3 came out
        
           | kro wrote:
           | Agree, Google made it really easy here, compared to using
           | service account certificates like with some of their other
           | APIs.
        
         | yawnxyz wrote:
         | I've to this day never been able to pay for Gemini through the
         | API, even though I've tried maybe 6-7 times
         | 
         | If you bring it up to Logan he'll just brush it off -- I
         | honestly don't know if they test these UX flows with their own
         | personal accounts, or if something is buggy with my account.
        
           | pants2 wrote:
           | This is my experience as well in my personal account, however
           | at work given we were already paying for Google Cloud it was
           | easy enough to connect a GCP account.
           | 
           | But somehow personally even though I'm a paying Google One
           | subscriber and have a GCP billing account with a credit card,
           | I get confusing errors when trying to use the Gemini API
        
           | bobviolier wrote:
           | https://x.com/OfficialLoganK/status/1978897746921693572?s=20
        
             | TheTaytay wrote:
             | Yes, I get the impression he has been fighting this fight
             | internally since the day he arrived. He can't exactly talk
             | about how infuriating it must be, but I look forward to his
             | memoir.
        
           | altbdoor wrote:
           | To Logan's credit though, his team made and drove a lot of
           | good improvements in AI studio and Gemini in general since
           | the early days.
           | 
           | I feel his team is really hitting a wall now in terms of
           | improvements, because it involves Google teams/products
           | outside of their control, or require deep collaboration.
        
         | BoorishBears wrote:
         | As the other comments pointed out, that's not covering
         | billing...
         | 
         | But also the (theoretical) production platform for Gemini is
         | Vertex AI, not AI Studio.
         | 
         | And until pretty recently using _that_ took figuring out
         | service accounts, and none of Google 's docs would demonstrate
         | production usage.
         | 
         | Instead they'd use the gcloud CLI to authenticate, and you'd
         | have to figure out how each SDK consumed a credentials file.
         | 
         | -
         | 
         | Now there's "express mode" for Vertex which uses an API Key, so
         | things are better, but the complaints were well earned.
         | 
         | At one point there were even features (like using a model you
         | finetuned) that didn't work without gcloud depending on if you
         | used Vertex or AI Studio: https://discuss.ai.google.dev/t/how-
         | can-i-use-fine-tuned-mod...
        
           | obmelvin wrote:
           | I could've made my comment more clear. Definitely missing a
           | statement along the lines of "and then after creating, you
           | click 'set up billing' and link the accounts in 15 seconds"
           | 
           | I did edit my message to mention I had GCP billing set up
           | already. I'm guessing that's one of the differences between
           | those having trouble and those not.
        
         | jiggawatts wrote:
         | Every aspect is at least partially broken several times a day,
         | and even when there isn't a temporary outage of something
         | somewhere, there are nonsensical "blocks" for things that ought
         | to just work.
         | 
         | I've been using the AI Studio with my personal Workspace
         | account. I can generate an API key. That worked for a while,
         | but now Gemini CLI won't accept it. Why? No clue. It just says
         | that I'm "not allowed" to use Gemini Pro 3 with the CLI tool.
         | No reason given, no recourse, just a hand in your face flatly
         | rejecting access to something I _am_ paying for and can use
         | elsewhere.
         | 
         | Simultaneously, I'm trying to convince my company to pay for a
         | corporate account of some sort so that I can use API keys with
         | custom tools and run up a bill of potentially thousands of
         | dollars that we can charge back to the customer.
         | 
         | My manager tried to follow the instructions and... followed the
         | wrong ones. They all look the same. They all talk about
         | "Gemini" and "Enterprise". He ended up signing up for Google's
         | equivalent of Copilot for business use, _not_ something that
         | provides API keys to developers. Bzzt... start over from the
         | beginning!
         | 
         | I did eventually find the instructions by (ironically) asking
         | Gemini Pro, which provided the convenient 27 step process for
         | signing up to three different services in a chain before you
         | can do anything. Oh, and if _any_ of them trigger any kind of
         | heuristic, again, you get a hand in face telling you firmly and
         | not-so-politely to take a hike.
         | 
         | PS: Azure's whatever-it-is-called-today is just as bad if not
         | worse. We have a corporate account and can't access GPT 5
         | because... I dunno. We just can't. Not worthy enough for access
         | to Sam Altman's baby, apparently.
        
       | postsantum wrote:
       | Congrats, you have sampled the life of android developer. I've
       | been avoiding touching Gemini exactly for the reason "Your
       | account is in good standing. For now". When it's not, enjoy your
       | ban for life
        
         | horaceradish wrote:
         | Apple as well. Apple developer sign up refuses to accept my
         | government issued ID.
         | 
         | So fuck them, I decided. Sold all my Apple hardware but phone
         | and watch. Downgraded phone to basic bitch when my last one
         | died
        
       | andy99 wrote:
       | I use OpenAI and Anthropic APIs every day for work. I have never
       | used google Gemini precisely because there seems to be a whole
       | different set of friction involved in getting an account. First I
       | don't want to tie anything to my google account, especially any
       | form of payment (no idea if I actually need to do this). Second I
       | don't want AI studio or whatever, I just want a similar api to
       | the others I can hit.
       | 
       | I admit I'm completely ignorant about what's really involved, I
       | have never tried and am just going on vague things I've heard but
       | stories like this definitely reinforce my perception. I even have
       | a mistral account, grok, etc, but google feels like a whole other
       | level of complication.
        
         | 0cf8612b2e1e wrote:
         | I feel you on not wanting to tie anything additional to your
         | Google account. Will I somehow do something "naughty" (say spam
         | an emoji during a livestream) that gets me permanently banned
         | for life from all services?
         | 
         | Google really needs to evaluate separating service bans. I
         | cannot be the only one who would rather go to a competitor than
         | risk angering the black box and destroying my digital life.
        
       | robertheadley wrote:
       | I had issues too, I wanted to use my free Google API credits with
       | Roo Code, but I could never get it to work. I eventually got
       | Gemini Cli and now Antigravity to work.
        
       | ryuuseijin wrote:
       | Just a note that you can use opencode with their API gateway
       | (they call it "zen") to get access to all the most popular models
       | using a single account, including gemini. (Although this wouldn't
       | have helped the author, since they wanted to try the Gemini CLI
       | specifically).
        
       | happyopossum wrote:
       | The underlying issue here is that 3.0 is still in preview. Once
       | it's a GA model, you can just use your $20 consumer Ai pro sub
       | and skip all the GCP stuff...
        
       | heystefan wrote:
       | I had the same experience. Plus you never know what's the best
       | way to use eg. Nano Banana -- it works better in AI Studio versus
       | their regular Gemini chat.
        
       | jpollock wrote:
       | There is a lot of fraud with UPI, specifically social engineering
       | to obtain UPI OTP codes.
       | 
       | Since the card and the account haven't been previously
       | associated, that's probably a risk model saying a human needs to
       | verify the account before activation.
       | 
       | Indian cards also (I believe) have a mandatory 24 notice period
       | prior to money being pulled - giving fraudsters a 24 hour
       | starting gun to spend like crazy. That makes merchants that
       | provide variable cost service on credit products twitchy.
       | 
       | https://support.stripe.com/questions/background-on-indian-go...
        
       | koinedad wrote:
       | I have always found Google products incredibly confusing and
       | difficult to use. I have had a very similar experience to this a
       | number of times.
        
         | antonvs wrote:
         | I work with GCP regularly. Once you're familiar with their
         | approach, it's straightforward enough. But the situation with
         | Gemini is on a whole different level.
        
       | intothemild wrote:
       | I like using Gemini for general stuff,
       | 
       | I have that Gemini AI plan thing, and it's great. But I
       | absolutely will not plug my credit card into Google cloud
       | services, no way.. I know I can put guardrails up, but I just am
       | terrified that I'll get a gigantic bill that I cannot afford.
       | 
       | Nope sorry no way. I want a simple $X per month sub.
       | 
       | Claude gives me that. Which is why Claude wins.
        
         | ra wrote:
         | That's fine but you're missing out, and you're most likely
         | paying waay more than you need to.
        
           | ipaddr wrote:
           | Missing out on nothing
        
       | btown wrote:
       | 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.
        
         | numlocked wrote:
         | (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.
        
       | g-unit33 wrote:
       | Wait until the 429 error message
        
         | wosat wrote:
         | 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.
        
       | rvnx wrote:
       | Setting up a limit of spending is even more difficult
        
         | movedx01 wrote:
         | Is that even possible? Last time I checked it wasn't, while it
         | was possible with OpenAI. Since that moment(early this year) -
         | OpenAI has removed that option and their "Project budget"
         | feature turned from being a hard limit into an email
         | notification.
        
       | senthilnayagam wrote:
       | I am from India, Have had similar experience. After billing they
       | mentioned models which ai was looking were not launched in india
       | ( Veo3 and nano banana )
       | 
       | I use replicate, fal for all api and for LLM openrouter
        
       | binarymax wrote:
       | The same billing experience applies to the Google programmable
       | search api. Easy to get a key, but a Byzantine maze to pay for
       | more than the free version.
        
       | eezing wrote:
       | It looks AI won't replace software engineers after all.
        
       | levocardia wrote:
       | Add me to the list of "saw nano banana pro, attempted to get an
       | API key for like 5min, failed and gave up." Maybe I am a dummy
       | (quite possible) but I have seen many smart people similarly
       | flummoxed!
       | 
       | You can walk into a McDonalds without being able to read, write,
       | or speak English, and the order touchscreen UI is so good (er,
       | "good") that you can successfully order a hamburger in about 60
       | seconds. Why can't Google (of all companies) figure this out?
        
         | JohnMakin wrote:
         | because the bubble in which googlers exist is inherently user-
         | hostile, even to their own detriment. been like this for a
         | while
        
           | CGamesPlay wrote:
           | The difference here is that many of Google's users are cost
           | centers, but in this case Google is being hostile to their
           | profit centers as well.
        
             | antonvs wrote:
             | I wonder if they actually see their current users as profit
             | centers. The tech is still being built out, to some extent
             | they just need users to find out how it gets used and to
             | get experience in the space. The real appeal of this entire
             | space is its future potential, so they just may not care
             | that much about providing a good consumer-grade experience
             | at this stage.
        
         | andy99 wrote:
         | I tried at some point to sign up for whatever IBMs AI cloud was
         | called. None of the documentation was up to date, when you
         | clicked on things you ended up in circular loops that took you
         | back where you started. Somehow there were several kinds of api
         | keys you could make, most seemingly decoys and only one correct
         | one. The whole experience was like one of those Mario castle
         | levels where if you don't follow the exact right pattern you
         | just loop back to where you started.
         | 
         | It makes sense for IBM, seems like google is just reaching that
         | stage?
        
         | drak0n1c wrote:
         | I use a third party API aggregator/forwarder (VeniceAI) for
         | this reason.
        
         | mrieck wrote:
         | At least Google models like Nano Banana Pro release Day 1 on
         | https://fal.ai
         | 
         | I made a free Chrome extension that uses Fal api key if you
         | want a UI instead of code
         | 
         | https://chromewebstore.google.com/detail/ai-slop-canvas/dogg...
        
       | squirrellous wrote:
       | As a former employee, the engineering culture at Google gives me
       | old-school hacker vibes, so users are very much expected to
       | "figure it out" and that's somewhat accepted (and I say this with
       | fond memories). It's no surprise the company struggles with good
       | UX.
        
         | gilrain wrote:
         | > users are very much expected to "figure it out" and that's
         | somewhat accepted
         | 
         | That sounds like a really fun place to work but a really awful
         | business to be a customer of.
        
       | huevosabio wrote:
       | This nonsense alone justifies the existence of OpenRouter.
        
       | msp26 wrote:
       | 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 more generous limits on the schemas and clearer docs.
       | https://platform.openai.com/docs/guides/structured-outputs#s....
       | 
       | You guys closed this issue for no reason:
       | https://github.com/googleapis/python-genai/issues/660
       | 
       | Other than that, good work! I love how fast the Gemini models
       | are. The current API is significantly less of a shitshow compared
       | to last year with property ordering etc.
        
       | KnuthIsGod wrote:
       | How long before Gemini is killed by Google and gets a nice grave
       | at Killed By Google ?
       | 
       | https://killedbygoogle.com/
       | 
       | I give it a single digit number of years.
        
       | arihant wrote:
       | I think now the Google One AI Pro subscription directly works for
       | raising limits on the CLI? But otherwise, there is an Individual
       | subscription. The problem is it doesn't work out of the box. You
       | have to create a whole Google Cloud project and attach the API to
       | it to get it to work. Otherwise the CLI would stop logging you
       | in, which it did when the account was free. The worst part is if
       | that cloud project had any code in it, CLI will use it as context
       | on every prompt.
        
       | KerrickStaley wrote:
       | In my personal experience, OpenRouter makes it easy to call
       | Gemini 3 Pro Preview and other frontier LLMs with very little
       | setup. It's great for projects where you want to compare
       | different LLMs or have the flexibility to switch. It charges a
       | 5.5% fee on top of the base API price so at scale you would want
       | to switch to directly calling the provider.
        
       | vinhnx wrote:
       | 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 month, I was charged over
       | $250 on my credit card, well beyond the free trial allowance. It
       | was entirely my fault for not setting a limit and not reviewing
       | the free trial terms more carefully.
       | 
       | That said, while setting up the Gemini API through AI Studio is
       | remarkably straightforward for small side projects, transitioning
       | to production with proper billing requires navigating the
       | labyrinth that is Google Cloud Console. The contrast between AI
       | Studio's simplicity and the complexity of production billing
       | setup is jarring, it's easy to miss critical settings when you're
       | trying to figure out where everything is.
        
         | edoceo wrote:
         | It seems that billing here (and elsewhere) for cloud is
         | intentionally opaque. Nearly every client (at scale) is having
         | (one of) a service provider to help manage/audit these usage.
         | 
         | Variable costs are great, scale with the business; but
         | visibility is a big (intentional?) challenge.
        
       | kunley wrote:
       | > I was fifteen minutes into writing some code by hand like a
       | Neanderthal
       | 
       | Tell me this isn't classism. Tell me this kind of narrative isn't
       | a new norm
        
         | antonvs wrote:
         | I can't tell if you might be joking. If you are, the rest of
         | this comment is irrelevant.
         | 
         | That general idiom is old and fairly widely used. There was a
         | Seinfeld episode in 1997 in which Elaine talked about "...not
         | lurching around like a caveman."
         | 
         | If you're objecting to criticism of writing code by hand, the
         | phrase is almost invariably used in a self-deprecating way,
         | acknowledging some inefficiency or old-fashioned behavior with
         | comic hyperbole. It's not criticizing people who write code by
         | hand as such - the author is criticizing themselves for doing
         | something the hard way.
        
           | kunley wrote:
           | Thank you. Seinfeld reference does it.
           | 
           | About the "hard way", everything in the article is screaming
           | that OP's new way of coding is the hard way, not the other
           | way around
        
             | gilrain wrote:
             | You came in hot with a wrong assumption couched in absolute
             | terms... and, after correction, you're flouncing out with
             | the same irrelevent message.
             | 
             | I'm an AI skeptic, but this ain't it.
        
             | antonvs wrote:
             | Isn't it just the Gemini key aspect that's hard? That's not
             | specific to this way of coding, just to Google's half-baked
             | mish-mash of offerings.
             | 
             | He should have used OpenAI or Anthropic - instead of using
             | Google, like a Neanderthal.
        
       | ankit219 wrote:
       | Think its a combination of factors.
       | 
       | - Google cloud is setup for big organizations. Not for
       | individuals. All cloud providers are pretty much confusing in a
       | similar way. - India has specific rules re cybersecurity and
       | financial regulations that Google has to comply. (mandatory id
       | verification and kyc compliance). Others have asked for an id
       | check too.
       | 
       | From what confused me, if OP wanted to use a model, the easier
       | way would have been to pay cursor/windsurf etc. and select that
       | model. Usually that is how people try out a new model. Trying out
       | a specific way means going through the norms every country
       | imposes, and bloat in case of legacy products.
       | 
       | AWS and Azure have come up with their own models. If their future
       | versions hit close to sota and people want to use it, many would
       | end up in a similar loop (and woudl be easier to just use it from
       | the aggregators).
        
       | doctorpangloss wrote:
       | Not being able to sign up for stuff is in the same league as
       | being perpetually low on disk space.
        
       | Ozzie_osman wrote:
       | 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 lacking in
       | some functionality), and the TTS API (which performed very poorly
       | despite offering the same models). They also have separate keys
       | (at least, Gemini vs Vertex).
       | 
       | 2. Each of those APIs supports different parameters (things like
       | language, whether you can pass a style prompt separate from the
       | words you want spoken, etc). None of them offered the full
       | combination we wanted.
       | 
       | 3. To learn this, you have to spend a couple hours reading API
       | docs, or alternatively, just have Claude Code read the docs then
       | try all different combinations and figure out what works and what
       | doesn't (with the added risk that it might hallucinate
       | something).
        
         | CSMastermind wrote:
         | Some other fun things you'll find:
         | 
         | - The models perform differently when called via the API vs in
         | the Gemini UI.
         | 
         | - The Gemini API will randomly fail about 1% of the time, retry
         | logic is basically mandatory.
         | 
         | - API performance is heavily influenced by the whims of the
         | Google we've observed spreads between 30 seconds and 4 minutes
         | for the same query depending on how Google is feeling that day.
        
           | DANmode wrote:
           | So, not something for a production app yet.
        
           | ianberdin wrote:
           | Even funnier, when Pro 3 answers to a previous message in my
           | chat. Just making a duplicate answer with different words.
           | Retry helps, but...
        
           | specproc wrote:
           | I have also had some super weird stuff in my output
           | (2.5-flash).
           | 
           | I'm passing docs for bulk inference via Vertex, and a small
           | number of returned results will include gibberish in
           | Japanese.
        
             | walthamstow wrote:
             | I had this last night from flash lite! My results were
             | interspersed with random snippets of legible, non-gibberish
             | English language. It was like my results had got jumbled
             | with somenone else's.
        
             | ashwindharne wrote:
             | I get this a lot too, have made most of the Gemini models
             | essentially unusable for agent-esque tasks. I tested with
             | 2.5 pro and it still sometimes devolved into random
             | gibberish pretty frequently.
        
           | hobofan wrote:
           | > The Gemini API will randomly fail about 1% of the time,
           | retry logic is basically mandatory.
           | 
           | That is sadly true across the board for AI inference API
           | providers. OpenAI and Anthropic API stability usually suffers
           | around launch events. Azure OpenAI/Foundry serving regularly
           | has 500 errors for certain time periods.
           | 
           | For any production feature with high uptime guarantees I
           | would right now strongly advise for picking a model you can
           | get from multiple providers and having failover between
           | clouds.
        
             | downsplat wrote:
             | Yeah at $WORK we use various LLM APIs to analyze text; it's
             | not heavy usage in terms of tokens but maybe 10K calls per
             | day. We've found that response times vary a lot, sometimes
             | going over a minute for simple tasks, and random fails
             | happen. Retry logic is definitely mandatory, and it's good
             | to have multiple providers ready. We're abstracting calls
             | across three different APIs (openai, gemini and mistral,
             | btw we're getting pretty good results with mistral!) so we
             | can switch workloads quickly if needed.
        
               | jwillp wrote:
               | I've been impressed by ollama running locally for my
               | work, involving grouping short text snippets by semantic
               | meaning, using embeddings, as well as summarization
               | tasks. Depending on your needs, a local GPU can sometimes
               | beat the cloud. (I get no failures and consistent
               | response times with no extra bill.) Obviously YMMV, and
               | not ideal for scaling up unless you love hardware.
        
               | duckmysick wrote:
               | Which models have you been using?
        
               | phantasmish wrote:
               | It'd be kinda nice if they exposed whatever queuing is
               | going on behind the scenes, so you could at least
               | communicate that to your users.
        
           | halflings wrote:
           | "The models perform differently when called via the API vs in
           | the Gemini UI."
           | 
           | This shouldn't be surprised, e.g. the model != the product.
           | The same way GPT4o behaves differently than the ChatGPT
           | product when using GPT4o.
        
           | te_chris wrote:
           | The way the models behave in Vertex AI Studio vs the API is
           | unforgivable. Totally different.
        
           | akhilnchauhan wrote:
           | > The models perform differently when called via the API vs
           | in the Gemini UI.
           | 
           | This difference between API vs UI responses being different
           | is common across all the big players (Claude, GPT models,
           | etc.)
           | 
           | The consumer chat interfaces are designed for a different
           | experience than a direct API call, even if pinging the same
           | model.
        
         | prodigycorp wrote:
         | Also, usage and billing takes a DAY to update. On top of that,
         | there are no billing caps or credit-based billing. They put the
         | entire burden on users not to ensure that they don't have a
         | mega bill.
        
           | paganel wrote:
           | > there are no billing caps or credit-based billing.
           | 
           | Was really curious about that when I saw this in the posted
           | article:
           | 
           | > I had some spare cash to burn on this experiment,
           | 
           | Hopefully the article's author is fully aware of the real
           | risk of giving Alphabet his CC details on a project which has
           | no billing caps.
        
             | nacozarina wrote:
             | there's prob a couple ppl out there with an Amex Black
             | parked on a cloud acct, lol
        
         | te_chris wrote:
         | Trying to implement their gRPC api from their specs and
         | protobufs for Live is an exercise in immense frustration and
         | futility. I wanted to call it from Elixir, even with our strong
         | AI I wasted days then gave up.
        
         | thecupisblue wrote:
         | 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" which will then splices it
         | into 1 FPS images and feeds it to the LLM. No option to improve
         | the FPS, so if you want anything properly done, you'll have to
         | splice it yourself and upload it to
         | generativelanguage.googleapis.com which is only accessible
         | using their GenAI SDK. Don't ask which one, I'm still not sure.
         | 
         | 6. Nice, it works. Let's try using live video. Open the docs,
         | you get it mentioned a bunch of times but 0 documentation on
         | how to actually do it. Only suggestions for using 3rd party
         | services. When you actually find it in the docs, it says "To
         | see an example of how to use the Live API in a streaming audio
         | and video format, run the "Live API - Get Started" file in the
         | cookbooks repository". Oh well, time to read badly written
         | python.
         | 
         | 7. How about we try generating a video - open up AI studio, see
         | only Veo 2 available from the video models. But, open up
         | "Build" section, and I can have Gemini 3 build me a video
         | generation tool that will use Veo 3 via API by clicking on the
         | example. But wait why cant we use Veo 3 in the AI studio with
         | the same API key?
         | 
         | 8. Every Veo 3 extended video has absolutely garbled sound and
         | there is nothing you can do about it, or maybe there is, but by
         | this point I'm out of willpower to chase down edgy edge cases
         | in their docs.
         | 
         | 9. Let's just mention one semi-related thing - some things in
         | the Cloud come with default policies that are just absurdly
         | limiting, which means you have to create a resource/account,
         | update policies related to whatever you want to do, which then
         | tells you these are _old policies_ and you want to edit new
         | ones, but those are impossible to properly find.
         | 
         | 10. Now that we've setup our accounts, our AI tooling, our
         | permissions, we write the code which takes less than all of the
         | previous actions in the list. Now, you want to test it on
         | Android? Well, you can:
         | 
         | - A. Test it with your account by signing in into emulators, be
         | it local or cloud, manually, which means passing 2FA every time
         | if you want to automate this and constantly risking your
         | account security/ban.
         | 
         | - B. Create a google account for testing which you will use,
         | add it to Licensed Testers on the play store, invite it to
         | internal testers, wait for 24-48 hours to be able to use it,
         | then if you try to automate testing, struggle with having to
         | mock a whole Google Account login process which every time uses
         | some non-deterministic logic to show a random pop-up. Then, do
         | the same thing for the purchase process, ending up with a giant
         | script of clicking through the options
         | 
         | 11. Congratulations, you made it this far and are able to
         | deploy your app to Beta. Now, find 12 testers to actively use
         | your app for free, continuously for 14 days to prove its not a
         | bad app.
         | 
         | At this point, Google is actively preventing you from shipping
         | at every step, causing more and more issues the deeper down the
         | stack you go.
        
           | egorfine wrote:
           | 12. Release your first version.
           | 
           | 13. Get your whole google account banned.
        
             | davidmurdoch wrote:
             | 14. Ask why it was banned and they respond with something
             | like "oh you know what you did".
        
               | short_sells_poo wrote:
               | Ha, bold of you to assume they'll respond!
        
       | CSMastermind wrote:
       | It's so terrible. I cannot tell you the hours I've wasted trying
       | to find a way to see all the Gemini API keys generated in my
       | organization and I have been unsuccessful. I've tried AI Studio,
       | GCP, and Google Admin.
       | 
       | We've reverted to everyone at the company just using the API key
       | I created because I can't figure out a way to give anyone else
       | visibility into keys and usage.
        
       | guelo wrote:
       | Not just gemini, my sense is that many of google's products are
       | collapsing in terms of confusing features and quality. I use to
       | be a fanboy but I've been painfully extracting myself from their
       | ecosystem, more because of the constant churn of product issues
       | than because of any political issues. I suspect it's an instance
       | of conway's law where the org chart has become a disaster after
       | all the layoffs and reorgs.
        
       | SamDc73 wrote:
       | A while back it took me around ~20 minutes to figure out how to
       | subscribe to Gemini CLI and when done I couldn't even verify
       | within the CLI ...
        
       | lxe wrote:
       | I always wondered how something like AWS or GCP Cloud Console
       | admin UIs get shipped. How could someone deliver a product like
       | these and be satisfied, rewarded, promoted, etc. How can Google
       | leadership look at this stuff and be like... "yup, people love
       | this".
        
         | jiggawatts wrote:
         | A purer, more perfect example of Conway's Law has never been
         | made more manifest than the myriad AWS consoles, each further
         | partitioned by region.
         | 
         | https://en.wikipedia.org/wiki/Conway%27s_law
         | 
         | And see especially _"The Only Unbreakable Rule"_ by Molly
         | Rocket: https://youtu.be/5IUj1EZwpJY
        
           | Aperocky wrote:
           | In defense of AWS consoles, they are derivative of AWS APIs,
           | as such they are really just a convenience layer that will
           | only occasionally string 2+ AWS APIs together for convenience
           | purposes that can be considered distinct feature on the
           | console.
           | 
           | That is wholly unlike the problem here where the console and
           | API somehow behaves completely differently.
        
             | ksimukka wrote:
             | Along with the public APIs, An AWS service can also have
             | Console APIs that are specifically for the console. These
             | APIs do not have the same constraints as the public api.
             | 
             | (My team built the MediaLive service)
        
         | theflyinghorse wrote:
         | What are the chances that Google leadership even seen GCP
         | interface outside of a demo once a never?
        
         | DANmode wrote:
         | Google doesn't have leadership, it has shareholders.
        
       | DeathArrow wrote:
       | It seems like they don't want to make money out of it right now
       | and it was mostly a show off to prove they can do it. That, or
       | massive incompetence.
        
       | Aeolun wrote:
       | This is exactly my experience with gemini, and exactly why I
       | bounced on the stupid thing. I just don't have hours to waste on
       | Google's stupid processes.
        
         | kkarpkkarp wrote:
         | And exactly same here. I wonder how much money they lose
         | because of this poor process.
         | 
         | I am not going to use Gemini API in foreseen future as I don't
         | want to manage those keys anymore. No matter how good their
         | model is
        
       | ianberdin wrote:
       | I had even worse experience with Microsoft Azure. In the middle
       | of the path I realized a third-party sales "ultra real Microsoft
       | support, certified" is dealing with me in order to sell me
       | overpriced options.
        
       | rand17 wrote:
       | So you don't like writing "the boring code". What do you expect
       | from writing a CRUD? What would you like to write? What
       | "interesting problems" would you like to focus on? Great sadness
       | will fall upon the industry when the last graybeard dies, who had
       | this arcane knowledge of "writing code". I have bad Player Piano
       | vibes nowdays.
       | 
       | Around me devs are beginning to warm up to the idea, that they
       | are not coders (and neither should I be), but "prompt engineers".
       | When I take too much time on a task, when I can't solve a problem
       | with a push of a button, when I muse about copilot hallucinations
       | in my PR - someone usually comes helpfully to tell me, I need
       | better prompting skills. Have you tried this expression? Have you
       | tried more context? Have you tried with this copy pasted magical
       | formula?
       | 
       | No creative worker in human history was so overjoyed to devalue
       | his or her work and knowledge in such haste.
        
         | mittensc wrote:
         | Other side of the equation:
         | 
         | I remember learning C++ with something like valgrind. I would
         | write stupid code, validate, fix stupid issues.
         | 
         | Others before me learned the harder way.
         | 
         | With LLMs right now I'm learning frontend by just generating
         | the UIs I want.
         | 
         | I'm getting the code/mocks and experimenting.
         | 
         | It's bad code, i will need to adjust, but it helps immensely as
         | a starting point same as valgrind helped in the past.
         | 
         | Trying to learn via searching for info just doesn't work as
         | well with all the flood of spam.
        
           | rand17 wrote:
           | I do not think that all LLMs are evil; they are valid tools,
           | but it's not a hammer with meta glasses attached to render
           | everything into a nail. I also find it very useful in certain
           | situations - but not in all situations.
           | 
           | Two more things. Bad code (in work, in reality, not in a
           | hobby project) is rarely converted into good code. And the
           | last one: in my twenty plus years of being a dev, this is the
           | first year job offers simply just dried up. With bad code
           | being good enough (hey, it compiles! it mostly works!),
           | hopefully you and I will be the lucky few to still be in the
           | business five years later.
        
             | mittensc wrote:
             | > Bad code (in work, in reality, not in a hobby project) is
             | rarely converted into good code
             | 
             | Most code everywhere is bad code. Nobody cares
             | unfortunately.
             | 
             | > And the last one: in my twenty plus years of being a dev,
             | this is the first year job offers simply just dried up.
             | 
             | Actions of the US gov have caused a recession.
             | 
             | It's hard to find jobs in that environment
             | 
             | Put the blame where it's due.
             | 
             | AI is an excuse.
             | 
             | No company is going to hire now because of that.
             | 
             | There is also heavy bloat of incompetent software
             | developers that needs to be shed.
             | 
             | Edit: Side note of shedding incompetent people
             | 
             | At work, I have a budget for tools, in the past this was
             | handed over to contractors (think accenture).
             | 
             | They would come back with estimates of 1+ months, multiple
             | developers and a manager for something I could do in a
             | week.
             | 
             | They would deliver very poor quality and I had no choice.
             | 
             | With LLMs I can do the same quality of work in 30 minutes,
             | then clean it up for a day and have a much better tool.
             | 
             | That budget is now used for other things and probably will
             | be cut due to economic uncertainty.
        
       | rozap wrote:
       | I wasted several hours this week going around in the exact same
       | circles. We have a billing account, but kept hitting a gemini
       | quota. Fine. But then on the quota page, every quota said 0%
       | usage. And our bill was like $5. Some docs said check AI studio,
       | but then the "import project from google cloud to AI studio"
       | button kept silently failing. This was a requests per minute
       | quota, which was set at 15 (not a whole lot...) but wouldn't
       | reset for 24 hours. So then I kept making new projects so I could
       | keep testing this thing I'm building, until eventually I ran out.
       | 
       | The only way we could get it resolved was to (somehow) get a real
       | human at google on the phone because we're in some startup
       | program or something and have some connection there. Then he put
       | in a manual request to bump our quota up.
       | 
       | Google cloud is the most kafkaesque insane system I've ever had
       | the misfortune of dealing with. Every time I use it I can tell
       | the org chart is leaking.
        
         | jacquesm wrote:
         | For the last decade or so I get a second $0.85 monthly bill
         | from google. Nobody at google knows why, but they recommend to
         | leave it because who knows what could be disabled if I block
         | those payments. Interesting detail here is that this is on a
         | bank account that we stopped using in 2017, so the only reason
         | we are keeping that account alive is for these stupid google
         | payments. In the cloud environment there is an invoice for the
         | amounts, but no way to change the billing info to our current
         | account and also no way (not by us, not by google support) to
         | figure out what these payments are actually for...
         | 
         | Calling it kafkaesque is giving it too much credit.
        
           | gikkman wrote:
           | I recently got an email saying a project I got is at the risk
           | of being disabled because my payment information is invalid.
           | But the card I got registered for it is the same I've had the
           | last two years, and it's still valid cause I used it
           | yesterday. Also, there is no amount due as far as I can tell.
           | I haven't done anything with the project for 6 month, it's
           | just sitting there. No API usage, nothing.
           | 
           | So I got no idea what to do to address it. I feel my best
           | option is wait for it to get disabled and try to address it
           | afterwards.
        
           | kyrra wrote:
           | Chargebacks or disputes will lock your account, so definitely
           | stay away from that path.
           | 
           | But just closing the bank account will stop auto billing
           | (it's considered a decline). So if you closed the account, it
           | would just stop paying for whatever it is, and then cloud may
           | lock the gcp account until it's paid. (I'm not 100% sure what
           | cloud does with unpaid invoices).
        
         | MrOrelliOReilly wrote:
         | I have been fighting the same bizarre quota demon. Scripts kept
         | timing out due to quota limitations, but I haven't been able to
         | find any indication of a limit in the console. Finally gave up
         | and switched to Claude, since they at least have a sane
         | interface for API keys and billing!
        
         | alexp2021 wrote:
         | Exactly the same for me. Quote usage is something like 2%, but
         | constantly experience the quota limit error.
        
           | Filligree wrote:
           | 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.
        
       | bobjordan wrote:
       | I went through similar song and dance using a paid Gemini code
       | assist "standard" level subscription. I finally got Gemini 3
       | working in my terminal in my repository. I assigned it a task
       | that Claude code Opus 4.5 would quickly knock out, and Gemini 3
       | did a reasonably similar job. I had opus 4.5 evaluate the work
       | and it was complimentary of Gemini 3S work. Then I check the
       | usage and I'd used 10% of the daily token usage limit, about 1.5M
       | tokens on that one task. So I can only get about 10 tasks before
       | I'm rate limited. Meanwhile with Claude code $200 max plan, I can
       | run 10 of those same caliber of tasks in parallel, even with opus
       | 4.5 model, and barely register the usage meter. The only thing
       | the Gemini code assist "standard" plan will be good for with
       | these limits are just double checking the plans that opus 4.5
       | makes. Until the usage limits are increased, it's pretty useless
       | compared to Claude code max plan. But there doesn't seem to be
       | any similar plan offering from Google.
        
       | asim wrote:
       | Unfortunately Google's problem is the product is dictated by the
       | architecture of the APIs and this is an issue for anything they
       | do. At one point long ago every Google product was disjointed and
       | Larry Page told everyone they needed to be unified under a single
       | theme and login. Then over time with the scale of the company you
       | become entirely dependent on the current workflows. To work
       | around it, all of a sudden there's a new UI for a new product and
       | it looks super clean right until you try do something with that
       | login or roles or an API key that has to effectively jailbreak
       | the flow you're in. Painful. It's why startups win. Small,
       | nimble, none of that legacy cruft to deal with. Whoever is
       | working hard to fix these problems at Google KUDOS TO YOU because
       | it's not easy. It's not easy to wrangle these systems across
       | hundreds of teams, products and infrastructure. The unification
       | and seamless workflow at that scale is painfully hard to achieve
       | and the issue is entirely about operating within the limitations
       | of the system but for good reason.
       | 
       | I hope they figure out a lot of the issues but at the same time,
       | I hope Gemini just disappears back into products rather than
       | being at the forefront, because I think that's when Google does
       | it's best work.
        
         | dbuxton wrote:
         | > The unification and seamless workflow at that scale is
         | painfully hard to achieve
         | 
         | It does make you wonder, why not just be a lot smaller? It's
         | not like most of these teams actually generate any revenue. It
         | seems like a weird structural decision which maybe made sense
         | when hoovering up available talent was its own defensive moat
         | but now that strategy is no longer plausible should be
         | rethought?
        
           | BozeWolf wrote:
           | And yet google generates around $1.9miljon revenue per
           | employee per year. Which is a lot, almost as good as
           | competitors.
        
           | asim wrote:
           | Two reasons. 1 - they print cash through Ads which means
           | there's opportunity or desire to do more things, or even a
           | feeling like you should or can. So new products emerge but
           | also to try diversify the revenue stream. 2 - the continuous
           | hiring and scale means churn, people get bored, they leave
           | teams, they want to do something new, it all bifurcates. It
           | keeps fragmenting and fragmenting until you have this
           | multilayered fractal. It's how systems in nature operate so
           | we shouldn't think corporation's will be any different. The
           | only way to mitigate things like this is putting in places
           | limits, rules and boundaries, but that also limits the upside
           | and if you're a public company you can't do that. You have to
           | grow grow grow and then cut cut cut and continue in that
           | cycle forever or until you die.
        
       | Simplita wrote:
       | I thought it was just me. The onboarding experience feels
       | unintentionally hostile for new developers.
        
       | krisgenre wrote:
       | Maybe they want more free users to better train their models and
       | don't care about the money (which they already have in plenty?).
       | 
       | In the grand scheme of things, paid users are minuscule. They are
       | probably delighted because of all the free users.
        
       | magictux wrote:
       | ahah I'm really vibing with this post, I went through the same
       | idea as the OP - wanted to try gemini 3 and/or nano banana - and
       | as soon as I was thrown into the billing management panel of
       | Google Cloud and their whole linking process I bailed.
        
       | aspenmayer324 wrote:
       | It's great that so many smart people are trying to fix this and
       | build something amazing. Let's hope it gets easier for everyone
       | soon!
        
       | journal wrote:
       | Won't be adding them then. Not worth the struggle from what I
       | read here. You think it's plug-n-play just swap a model id and
       | endpoint, nope, Chuck Testa.
        
       | srijanshukla18 wrote:
       | Yes, tried countless hours and even reached out to google billing
       | support. Doesn't accept UPI or card, runs into an error with
       | both.
        
       | dvorka wrote:
       | This is so true! But the adventure doesn't end there. I have 2
       | billing accounts from the past when I was building projects on
       | AppEngine. Annual exercise to keep them alive (even if no action
       | is needed in the end) is of similar complexity. Why do I need
       | these accounts? Because I want to use Google services for which I
       | don't pay.
        
       | arand wrote:
       | a hack you this went to a can go to you so good
       | hahahahahaSShahSSaha
        
       | runtimepanic wrote:
       | The experience feels fragmented because Google has multiple
       | overlapping developer consoles and product boundaries. Gemini
       | just exposes that underlying fragmentation more clearly than
       | other APIs.
        
       | dsmurrell wrote:
       | I avoid using Google because their cloud service product is so
       | badly designed.
        
       | wg0 wrote:
       | I love Google's product managers. I love product managers in
       | general but Google's product managers are at a whole another
       | level. And it shows.
        
       | GuestFAUniverse wrote:
       | Oh, another Google API rant.
       | 
       | I knew I never want to use another Google service as soon as I
       | got rclone running with my Google Drive:
       | https://rclone.org/drive/
       | 
       | I rather not waste my time with such abominations. And I don't
       | mean rclone. I don't care about the "history" of that API, or any
       | API. It's like strangers telling you their live's story at the
       | first meeting. Awkward.
        
       | odie5533 wrote:
       | The difficult process is on purpose. You're too small. You're
       | just going to waste their customer support resources and only
       | give them maybe a couple hundred dollars. They're hoping you give
       | up and go away.
        
         | mijoharas wrote:
         | We're a reasonably sized company. Recently we needed to change
         | our google cloud payment details.
         | 
         | Finance users had changed in the meantime, so I navigate and
         | create an iam user, ok, billing administrator is a thing,
         | great.
         | 
         | Oh, they said it didn't work? alright, there seems to be a
         | project billing administrator as well as an organisation
         | billing administrator? weird, ok let's try that.
         | 
         | Hmm... it still didn't work? let's look around a little more.
         | Ok, within the billing account (that they're a billing
         | administrator to) and within the organisation (that they're a
         | billing administrator to) there is a tab called "payment
         | users". This seems to be _separate_ from their IAM users, and
         | the person needs to be added there (as well as? instead of? who
         | knows) and _then_ they can change the card details.
         | 
         | UX is especially crap here (for google cloud billing).
         | 
         | Let's not even get started on the whole vertex vs. aistudio
         | stuff. Also when one of the gemini's came out their python
         | library worked while their curl docs, and their ruby client
         | didn't so we had to read the source of the python library to
         | figure out what it actually did under the hood to test it out.
         | (this was a while ago, I think they might've gotten better
         | since but the documentation/devex was really bad at at the
         | time)
        
       | jwr wrote:
       | I also tried to make Gemini work with opencode and after spending
       | about an hour in various panels, billing settings, setting up
       | access groups, project groups, and other paraphernalia, gave up.
       | There is Google Cloud, Vertex AI, Oauth which works or does not
       | depending on whatever, all the "groups" and other crap I don't
       | need, overall I just failed.
       | 
       | Claude code just works.
        
       | scirob wrote:
       | Agreed, only thing that kinda makes up for the huge number of
       | steps is that the GCP build in Ai assistant is actually great at
       | telling you what to do via CLI
        
       | phromo wrote:
       | I had a similar experience. However I gave up before being able
       | to pay. Repeated the story two or three times. This was work for
       | a medium sized Corp and in the end we didn't even give gemini a
       | chance because of this (performance was sufficiently good with
       | competing providers) . Really hope they up their UX.
        
       | windex wrote:
       | Google's interface, UX and information flow is complete
       | spaghetti. You never know what you will find and where. There is
       | no one you can call either. I suspect they abandon their products
       | because 50% of potential customers abandon their cart due to the
       | workflow.
        
       | crocowhile wrote:
       | I got a Gemini API key once. I was overcharged PS350, took me
       | ages to find a way to file a complain, and at the end they
       | refunded me only the google charges and not the VAT.
       | 
       | Never again, thanks.
        
       | sylware wrote:
       | You should be able to create an API account with a classic
       | noscript/basic (x)html browser (optionally with an email, and
       | that could be an IPv[46] literal email address, you know, self-
       | hosted & DNS free, which is stronger than SPF...).
       | 
       | Then to pay for, I should be able to redeem a code bought at my
       | local and physical monetary terminals (no credit card info input
       | on an internet able computer, even if elf/linux and lean classic
       | noscript/basic (x)html web browsers) that to add credits on my
       | account. Like steam. In my country, we even have codes for age
       | verification only (you have physical age verification like when
       | you buy alcohol from a [bottle] shop), much easier to crack down
       | on abuse.
       | 
       | Another thing could be a public "anonymous", severely rate
       | limited, API key for 'testing purpose' or very rare usage, or a
       | noscript/basic (x)html web site (namely a real and honest web
       | site) with ads (text/image/videos[<video>])... and with solid
       | handling of HTTP refresh?
       | 
       | My main usage for AI would be coding. I am craving at mass
       | porting C++ to a plain and simple subset of C code (it seems some
       | people are getting reasonably good results, and it seems rust has
       | a brain damaged syntax on the scale of c++), and assembly coding
       | with very specialized code snippet.
        
       | bambax wrote:
       | I went through the same nightmare a couple of months ago; in
       | frustration I sent a not very nice email to support. They did
       | respond a week later, saying everything was "fixed". But by that
       | time I had moved on, and will probably never come back.
       | 
       | But I wonder how it can happen that a bunch of obviously
       | extremely smart people can create such absurd Rube Goldberg
       | machines -- without the fun part.
        
         | brap wrote:
         | Leadership roles, especially in large corporations, often favor
         | people who are opportunistic. They don't care about the
         | product, they want that promo.
         | 
         | And to win that promo you have to ship big and ship fast. So
         | often times what you see is people delivering vaporware that
         | has the _appearance_ of high quality (lots of promises, looks
         | amazing in the slides deck, carefully selected data shows great
         | numbers, etc). It's a gamble, and sometimes it pays off.
         | 
         | By the time people accept that it's hot garbage, the leaders
         | have already moved on to the next opportunity. And it's not
         | that they were able to fool their managers, because their
         | managers are playing the same game on an even larger scale, so
         | they care even less.
         | 
         | Of course, this is not always the case. But there is a bias,
         | and it tends to show up more in large organizations
         | (government, large corporations, etc.)
        
       | erdemo wrote:
       | I am glad to see someone write about this, google API dashboards
       | are ... crap.
        
       | temp1611 wrote:
       | Google is the most political, extractive and dysfunctional cloud
       | from a customer point of view.
       | 
       | 1. Startup credits require multiple follow-ups, meetings, etc.
       | And these reps have weird incentive structures (so they are
       | trying to bypass each other to meet their quotas or whatever).
       | 
       | 2. Billing is opaque, you get charged for things you haven't used
       | 
       | 3. Support is outsourced - and it takes 4-5 exchanges with this
       | external vendor come to the central issue (by then usually people
       | just give up I guess)
       | 
       | 4. Overall behavior from various Google staff has been high-
       | handed - to say the least
       | 
       | Every other cloud provider has done better than Google in our
       | experience - AWS, Azure, Digital Ocean, OVH - all of them are
       | better to deal with.
       | 
       | I like to tell my team there are two G's in our life: (1) Google
       | and (2) Government, and these days the second G often does better
       | than first :)
        
         | thecupisblue wrote:
         | >Startup credits require multiple follow-ups, meetings, etc.
         | And these reps have weird incentive structures (so they are
         | trying to bypass each other to meet their quotas or whatever).
         | 
         | Man, I tried going for the credits. I've organised meetups and
         | conferences for Google, gave talks, been a part of Google
         | Startup campus for years now, have been invited to participate
         | in GDE program, and as I'm making a GenAI startup I decided
         | "well, maybe time to try getting those 300k cloud credits, I've
         | given them so much I'll surely get it".
         | 
         | Well, the first person I talked to, said I'm denied, because
         | they didn't even check the websites I added in the description.
         | They said oh I need to add it to another field for their team
         | to see, told me to update it, but there is no way to update it.
         | Then we had a second call, they said it's okay I can ignore
         | that and pointed me to another person who will be my "account
         | manager".
         | 
         | That person was absolutely uninterested into what we're doing,
         | what we want and what we plan to do. They did not even care
         | about helping us much until we reached 15k monthly spend or so,
         | giving a holier-than-thou attitude and sounding like they're
         | making lunch during the call. I'd rather have the call with an
         | LLM at this point.
         | 
         | Then even though our website says our product relies on AI, it
         | is impossible without AI and I explained to him how and why we
         | train custom models and use their GenAI products - the person
         | decided we are not an AI company and can only get 2k in Cloud
         | credits.
         | 
         | The interaction left such a sour taste in my mouth that I will
         | _never_ use Google Cloud in our product, as I do not want to
         | have to deal with the Account Manager.
        
       | lysecret wrote:
       | I see this, a hot take form my side as someone who is bought in
       | to GCP i quite like being able to put everything on the same
       | billing account / handle it easily through service accounts.
        
       | francoispiquard wrote:
       | I think they are trying too much to have you jump on GCP. Having
       | a simpler UI with a credit limit (maybe even at a different rate)
       | would actually get more people to use it imo.
        
       | therealmarv wrote:
       | Try to get a Google Vertex API key working locally. It's even
       | more complicated. Took me literally one full day to get the whole
       | toolchain working (had to do some pauses out of frustration).
       | 
       | I only went through it because I got once 300 USD for free to
       | spend on my Google Workspace account I/my business owns.
       | 
       | OpenAI API usage is so much easier.
       | 
       | Btw Google: Fix Google Console API usage dashboard... why is
       | there a delay of 2+ days? Why cannot I see (and block!) the usage
       | of the current day?
        
       | rodolphoarruda wrote:
       | Using metaphors is dangerous, but I would dare to say that big
       | tech AI is like cement suppliers. It's too low level of a
       | service. In civil engineering you have the option to contract
       | value added suppliers that will give you prefabricated pieces in
       | concrete or steel you could be using to build your construction.
       | 
       | I'm seeing a lot of AI firms building value added services on top
       | of big tech "foundational" AI offerings. Value addition can start
       | very early at a clear plans/billing structure, going through rate
       | limiting, documentation and extra features that will bring
       | stability or consistency to our AI enhanced products.
       | 
       | Going the other way around (I tried) and building things on top
       | of big tech AI is challenging starting at the fundamentals as the
       | OP described well.
        
         | wongarsu wrote:
         | Openrouter is roughly at that level of value-add. With plenty
         | of competition now, since being able to charge 5% on your AI
         | spend just for having sane billing, spending controls (actually
         | enforced per-api-token budget limits!) and easy sign-up is an
         | insanely profitable business proposition
         | 
         | On the other hand I think it's fair to criticize the model
         | hosts for not offering the same
        
           | numlocked wrote:
           | (I work at OpenRouter) Certainly for individual developers /
           | hobby projects that's the primary value prop; super easy
           | access to all of the models.
           | 
           | But there's a _lot_ more functionality that becomes relevant
           | when building in production. We do automatic fallbacks, route
           | between providers based on data policies, syndicate your data
           | to agent observability tools  / your logging platform of
           | choice, user-level and api-key-level budget management and
           | model allow/block lists, programmatic API key management,
           | etc, etc. More good stuff shipping all the time!
        
       | h33t-l4x0r wrote:
       | Did you ask Gemini how to do it? _ducks rotten tomatoes_ -
        
         | gilrain wrote:
         | Yes, that's part of the article you didn't read.
        
       | homakov wrote:
       | i wasted an hour setting up a key. Antigravity rejected me even
       | though my VPN was set to New York.
       | 
       | Nowhere close to claude/codex experience. Unusable dev experience
        
       | twsted wrote:
       | Same for me. Tried just a few days ago and, frustrated, gave up.
        
       | tgtweak wrote:
       | Have you looked at getting a gpt api key for gpt5? you have to do
       | selfie-ID verification...
        
       | drob518 wrote:
       | Yea, I went through this exact fiasco a few months ago trying to
       | do the same thing. Or rather, I went through the first two-thirds
       | of it and then gave up.
        
       | Arubis wrote:
       | Similarly to DeepSeek, this--more than dealing with different
       | APIs and routing--is the problem OpenRouter actually solves for
       | me.
        
       | nkotov wrote:
       | I had a similar experience with GCP / Google Workspace. It's just
       | bad experience.
        
       | happyopossum wrote:
       | There are plenty of ways to get access to gemini - a single
       | google search took me directly to the simplest way (subscribe to
       | Google AI Ultra) in one click:
       | https://one.google.com/intl/en/about/google-ai-plans/
       | 
       | The author apparently found himself on a much more difficult
       | path, one designed for enterprises who are already on google
       | cloud, already have billing set up, etc. The fact that an
       | individuals experience with an enterprise platform isn't great is
       | predictable... That's why there are individual/consumer plans for
       | this stuff.
        
         | Alifatisk wrote:
         | The url you sent, when signing up, just sends me to my homepage
         | where I get a overview of my subscription at one.google.com, I
         | can't see where to access a api key
        
         | 85392_school wrote:
         | Does it let you use Gemini 3 in Gemini CLI?
        
       | AmazingTurtle wrote:
       | Yeah and people keep posting shit about how google will win over
       | openai due to their "long breath"
        
       | m3kw9 wrote:
       | is a land min in that UI interface, you never know what you
       | enabled/disabled and get fked over by charges that came out of
       | left field, or why it doesn't work. google continues to be a UX
       | shit show
        
       | logankilpatrick wrote:
       | Hey! Very valid feedback on setting up a billing account. This is
       | something I have been pushing for over the last 2 years at
       | Google. The good news: setting up billing directly in AI Studio
       | tested internally and will be shipped in January : )
       | 
       | Will follow up on some of the other threads in here!
        
         | mseri wrote:
         | Finally! Great to hear. I had the exact same experience, but
         | gave up at the moment of ID verification... too much hassle
         | indeed
        
         | mrieck wrote:
         | Will that change also allow paying upfront ($250 or whatever)
         | to bump up a tier?
         | 
         | I want to release a service using computer-use but am worried
         | about 429 quota errors if I have actual users.
        
         | whalesalad wrote:
         | > setting up billing directly in AI Studio tested internally
         | and will be shipped in January
         | 
         | Does this mean I can finally use premium features without
         | onboarding my entire google workspace? I made the mistake of
         | getting a good chunk of my family on my google app domain back
         | in ~2007. For the last few years, I spend $80 per month just to
         | host their email because the cost is easier to deal with than
         | the human beings themselves. But I want to use the latest
         | premium Google AI tooling and as far as I can tell the only way
         | to do that is to upgrade my google workspace to the next tier
         | and blow even more $$$ away each month. Suffice to say I have
         | not done this, but it is a blocker from using things like Nano
         | Banana with a non-gmail account.
        
       | arjunchint wrote:
       | We built an AI Web Agent on top of Gemini.
       | 
       | We actually created shortcut for the agent itself to go to AI
       | Studio, create API key, and configure itself haha:
       | https://www.youtube.com/watch?v=L6ywfLrG_W8
        
       | cicloid wrote:
       | Amazon has Q, Google Gemini, Microsoft Copilot...
       | 
       | Names that mean everything, nothing or something based on what
       | website you land or what sales pipeline you are on.
        
       ___________________________________________________________________
       (page generated 2025-12-11 23:02 UTC)