alt Hacker NewsGetting a Gemini API key is an exercise in frustration
Comments
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 :)
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.
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.
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.
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.
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.
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.
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
Gemini API keys are an absolute delight compared to VertexAI. It’s like Google decided the most important part of competing with AWS was a horrific console.
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.
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).
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.
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.
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.
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
Yes, tried countless hours and even reached out to google billing support. Doesn't accept UPI or card, runs into an error with both.
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 …
Have you looked at getting an openai api key for gpt5? you have to do selfie-ID verification...
I had a similar experience with GCP / Google Workspace. It's just bad experience.
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.
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.
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.
I am glad to see someone write about this, google API dashboards are ... crap.
Same for me. Tried just a few days ago and, frustrated, gave up.
I avoid using Google because their cloud service product is so badly designed.
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
Similar experience for our business
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.
It looks AI won’t replace software engineers after all.
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!
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.
How long before Gemini is killed by Google and gets a nice grave at Killed By Google ?
I give it a single digit number of years.
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.
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.
I find GCP frustrating (coming from AWS) but luckily asking Gemini how to do things makes it much easier.
Did you ask Gemini how to do it? ducks rotten tomatoes-
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
1. I typed "How do I get a gemini api key" in my chrome bar
2. Firs line in the top result said "click here and then click the Get Key Button". I clicked the link and went to the page.
3. On the page I clicked "Get Key"
4. I named the key, then selected "New project" from the dropdown. I named the new project
5. I now have a key.
I actually timed myself, it took 34 seconds. This is a garbage ragebait post.
Yeah and people keep posting shit about how google will win over openai due to their "long breath"
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.
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.
Not being able to sign up for stuff is in the same league as being perpetually low on disk space.
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.
This nonsense alone justifies the existence of OpenRouter.
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
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.
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.