Comment by ceroxylon
21 hours ago
Google has been stomping around like Godzilla this week, and this is the first time I decided to link my card to their AI studio.
I had seen people saying that they gave up and went to another platform because it was "impossible to pay". I thought this was strange, but after trying to get a working API key for the past half hour, I see what they mean.
Everything is set up, I see a message that says "You're using Paid API key [NanoBanano] as part of [NanoBanano]. All requests sent in this session will be charged." Go to prompt, and I get a "permission denied" error.
There is no point in having impressive models if you make it a chore for me to -give you my money-
First off, apologies for the bad first impression, the team is pushing super hard to make sure it is easy to access these models.
- On permission issue, not sure I follow the flow that got you there, pls email me more details if you are able too and happy to debug: Lkilpatrick@google.com
- On overall friction for billing: we are working on a new billing experience built right into AI Studio that will make it super easy to add a CC and go build. This will also come along with things like hard billing caps and such. The expected ETA for global rollout is January!
Congrats on the move to Google!
Please allow me to rant to someone who can actually do something about this.
Vertex AI has been a nightmare to simply sign up, link a credit card, and start using Claude Sonnet (now available on Vertex AI).
The sheer number of steps required for this (failed) user journey is dizzying:
* AI Studio, get API key
* AI Studio, link payment method: Auto-creates GCP property, which is nice
* Punts to GCP to actually create the payment method and link to GCP property
* Try to use API key in Claude Code; need to find model name
* Look around to find actual model name, discover it is only deployed on some regions, thankfully, the property was created on the correct region
* Specify the new endpoint and API key, Claude Code throws API permissions errors
* Search around Vertex and find two different places where the model must be provisioned for the account
* Need to fill out a form to get approval to use Claude models on GCP
* Try Claude Code again, fails with API quota errors
* Check Vertex to find out the default quota for Sonnet 4.5 is 0 TPM (why is this a reasonable default?)
* Apply for quota increase to 10k tokens/minute (seemingly requires manual review)
* Get rejection email with no reasoning
* Apply for quota increase to 1 token/minute
* Get rejection email with no reasoning
* Give up
Then I went to Anthropic's own site, here's what that user journey looks like:
* console.anthropic.com, get API key
* Link credit card
* Launch Claude Code, specify API key
* Success
I don't think this is even a preferential thing with Claude Code, since the API key is working happily in OpenCode as well.
You went further with GCP than I did. I was asked repeatedly by support to contact some kind of a Google sales team.
I get the feeling GCP is not good for individuals like I. My friends who work with enterprise cloud have very high opinion about their tech stack.
1 reply →
Give up i think
Then you actually use it! I dare someone to try and get Gemini live vertex app working.
Just a note that your HN bio says "Developer Relations @OpenAI"
Sure it will get updated to same as Linkedin - Helping developers build with AI at Google DeepMind.
Imagine many on here have out of date bio's and best part - it don't matter, but sure can make some funnies at times.
1 reply →
I was interested. I does look like he just needs to update that. His personal blog says google, and ex-openAI. But I do feel like I have my tin foil on every time I come to HN now.
Pretty funny! I wonder how much of a premium Google is paying.
When we first started using Gemini for a new product a few months ago you banned our entire GCP account from using at all Gemini in the middle of a demo to our board. Doesn't seem like things have improved all that much on the on boarding front.
Maybe the team should push hard before releasing the product instead of after to make it work.
But then we'd complain about Google being a slow moving dinosaur.
"Move fast and break things" cuts both ways !
(ex-Google tech lead, who took down the Google.com homepage... twice!)
10 replies →
Imagining the counterfactual (“typical, the most polished part of this service is the payment screen!”), it seems hard to win here.
1 reply →
That’s a pretty uncharitable take. Given the scale of their recent launches and amount of compute to make them work, it seems incredibly smooth. Edge cases always arise, and all the company/teams can really do is be responsive - which is exactly why I see happening.
6 replies →
Any chance that this reflected to our company account instead of AI Studio?
We want to switch to Gemini from Claude (for agentic coding, chat UI, and any other employee-triggered scenarios) but the pricing model is a complete barrier: How do we pay for a monthly subscription with a capped price?
You launched Antigravity, which looks like an amazing product that could replace Claude Code, but do I know I will be able to pay for it in the same way I pay Claude, which is a simple pay per month subscription?
Just make it a VSCode plugin, I don't want to install a new IDE (which is just VSCode anyway) to use your product. It might be better than claude and chatgpt5.1 but not better enough to justify me re-doing all my IDE configs.
There is a Gemini VSCode plugin: https://marketplace.visualstudio.com/items?itemName=Google.g...
The new releases this week baited me into business ultra subscription. Sadly it’s totally useless for gemini 3 cli and now also nano banana does not work. Just wow.
I bought a Pro subscription (or the lowest tier paid plan, whatever it's called), and the fact that I had to fill out a Google Form in order to request access to get Gemini 3 CLI is an absolute joke. I'm not even a developer, I'm a UX guy who just likes playing around with seeing how models deal with importing Figma screens and turn them into a working website. Their customer experience is shockingly awful, worse than OpenAI and Anthropic.
Oh man, there is so, so much pain here. Random example - if GOOGLE_GENAI_USE_VERTEXAI=true in your environment, woe betide you if you're trying to use gemini cli with an API key. Error messages don't match up with actual problems, you'll be told to log in using the cli auth for google, then you'll be told your API keys have no access.. It's just a huge mess. I still don't really know if I'm using a vertex API key or a non-vertex one, and I don't want to touch anything since I somehow got things running..
Anyway vai com dios, I know that there's a fundamental level of complexity deploying at google, and deploying globally, but it's just really hard compared to some competitors. Sadly, because the gemini series is excellent!
Please make sure that the new billing experience has support for billing limits and prepaid balance (to avoid unexpected charges)!
Lol. Since the GirlsGoneWild people pioneered the concept of automatically-recurring subscriptions, unexpected charges and difficult-to-cancel billing is the game. The best customer is always the one that pays but never uses the service ... and ideally has forgotten or lost access to the email address they used when signing up.
2 replies →
Hi, is your team planning on adding a spending cap? Last I tried, there was no reasonable way to do this. It keeps me away from your platform because runaway inference is a real risk for any app that calls LLMs programatically.
The fact that your team is worrying about billing is...worrying. You guys should just be focused on the product (which I love, thanks!)
Google has serious fragmentation problems, and really it seems like someone else with high rank should be enforcing (and have a team dedicated to) a centralized frictionless billing system for customers to use.
This is nice that you know about the issue and are working on it. I really appreciate all the new "Get api key" buttons across google ai products that already makes it much easier than setting up a cloud project and getting credentials json files.
But I do think it's a general problem with Google products that the solution is always to build a new one. There are already like 8 ways to use and pay for Google AI and that adds to the complexity of getting set up, so adding a new simpler better option might make that all worse instead of better
Maybe if the sign up process encouraged people to send videos (screen-side and user-side could be useful also), of their sign-up and usage experience, the teams responsible for user experience could make some real progress. I guess the question is, who cares, or who is responsible in the organization?
Can we get free Nano Banana in AI studio at least in super low resolution? For app building and testing purposes it will be fine and cheap enough for you to make it possible?
Hopefully the mobile version of AI Studio gets some improvement. There are some pretty awful UI bugs that make it really difficult to use in a mobile first manner.
Though I still managed to vibe code an app using nanobanana. Now I just need to sort API billing with it so I can actually use my app.
Dude. Let me give you my money. This isn’t rocket science. I don’t want anything to do with Google Cloud or Google Workspace or w/e it’s called now. Let me just subscribe to Gemini or Nano straight up.
This should be like 2 clicks.
I had the same reaction as them many months ago, the Google Cloud and Vertex AI stuff namespacing is a too messy. The different paths people might take to learning and trying to use the good new models needs properly mapping out and fixing so that the UX makes sense and actually works as they expect.
I had pretty much written off ever my credit card to Google, but a better billing experience and hard billing caps might change that.
[flagged]
Google APIs in general are hilariously hard to adopt. With any other service on the planet, you go to a platform page, grab an api key and you’re good to go.
Want to use Google’s gmail, maps, calendar or gemini api? Create a cloud account, create an app, enable the gmail service, create an oauth app, download a json file. Cmon now…
Yeah, I'm not a dev and not using AI at all but had a need to create oauth keys and some APIs for some project... sometimes it works sometimes it doesnt and it's so complicated...but got it working in the end, thos it stops working after some time, it was like, Google, really?
If it's just the API you're interested in, Fal.ai has put Nano-Banana-Pro up for both generative and editing. A great deal less annoying to sign up for them since they're a pretty generalized provider of lots of AI related models.
https://fal.ai/models/fal-ai/nano-banana-pro
In general a better option, in the early days of AI video I tried to generate a video of a golden retriever using Google's AI Studio. It generated 4 in the highest quality and charged me 36 bucks. Not a crazy amount but definitely an unwelcome suprise.
Fal.ai is pay as you go and has the cost right upfront.
Vertex AI Studio setting a default of 4 videos where each video is several dollars to generate is a very funny footgun.
100% agreed. Same reason that I use the OpenRouter API for most LLM usage.
Is there a model on Fal.ai that would make it easy to sharpen blurry video footage? I have found some websites, but apparently they are mostly scammy.
Unfortunately, this is a fairly difficult task. In my experience, even SOTA models like Nano Banana usually make little to no meaningful improvement to the image when given this kind of request.
You might be better off using a dedicated upscaler instead, since many of them naturally produce sharper images when adding details back in - especially some of the GAN-based ones.
If you’re looking for a more hands-off approach, it looks like Fal.ai provides access to the Topaz upscalers:
https://fal.ai/models/fal-ai/topaz/upscale/image
1 reply →
You want a deconvolution pipeline like https://bartwronski.com/2022/05/26/removing-blur-from-images...
Or more likely https://www.cse.cuhk.edu.hk/~leojia/projects/motion_deblurri... for video
FYI that is an extremely challenging thing to do right. Especially if you care about accuracy and evidentiary detail. Not sure this is something that the current crop of AI tools are really tuned to do properly.
1 reply →
I'm dimestore cheap, I'd be exploding to frames and sharpening and reassembling with a ffmpeg>irfanview process Lol. It would be awfully expensive to do it with an AI model and the results would be expensive. Would a photo/video editing suite do it? Google photos with a pro script, or Adobe premiere elements, or would you be able to do it in yourself in DaVinci resolve? Or are you talking hundreds of hours of video?
There's the solution right there. Google is still growing its AI "sea legs". They've turned the ship around on a dime and things are still a little janky. Truly a "startup mode" pivot.
While we're on this subject of "Google has been stomping around like Godzilla", this is a nice place to state that I think the tide of AI is turning and the new battle lines are starting to appear. Google looks like it's going to lay waste to OpenAI and Anthropic and claim most of the market for itself. These companies do not have the cash flow and will have to train and build their asses off to keep up with where Google already is.
gpt-image-1 is 1/1000th of Nano Banana Pro and takes 80 seconds to generate outputs.
Two years ago Google looked weak. Now I really want to move a lot of my investments over to Google stock.
How are we feeling about Google putting everyone out of work and owning the future? It's starting to feel that way to me.
(FWIW, I really don't like how much power this one company has and how much of a monopoly it already was and is becoming.)
Valid questions, but I'd say that it's hard to know what the future holds when we get models that push the state of the art every few months. Claude sonnet 3.7 was released in February of this year. At the rate of change we're going, I wouldn't be surprised if we end up with Sonnet 5 by March 2026.
As others have noted, Google's got a ways to go in making it easier to actually use their models, and though their recent releases have been impressive, it's not clear to me that the AI product category will remain free from the bad, old fiefdom culture that has doomed so many of their products over the last decade.
We can't help but overreact to every new adjustment on the leader boards. I don't think we're quite used to products in other industries gaining and losing advantage so quickly.
This is also my take on the market, although I also thought it looked like they were going to win 2 years ago too.
> How are we feeling about Google putting everyone out of work and owning the future? It's starting to feel that way to me.
Not great, but if one company or nation is going to come out on top in AI then every other realistic alternative at the moment is worse than Google.
OpenAI, Microsoft, Facebook/Meta, and X all have worse track records on ethics. Similarly for Russia, China, or the OPEC nations. Several of the European democracies would be reasonable stewards, but realistically they didn't have the capital to become dominant in AI by 2025 even if they had started immediately.
1 reply →
100% this. I am using the pro/max plans on both claude and openai. Would love to experiment with gemini but paying is next to impossible. Why do i need the risk of a full blown gcp project just to test gemini. No thx.
Easiest way is to go https://aistudio.google.com/api-keys set up an api key and add your billing to it.
So much this. The entire experience around using Google's AI API's is a complete shit-show. I was (stubborn|obstinate|stupid|whatever) enough to keep dicking around until I actually got some stuff working (a few weeks ago) but I still feel dirty from the whole process. And I still don't know what I'm using (Gemini? AI Studio? Vertex? GCP? Other??) or how all of this crap relates.
And FSM forbid I have another time when my debit card number gets compromised and I have to try changing it with Google. That was even MORE painful than just trying to get things working in the first place. WTF am I editing, my GCP account or my Google account? Are those two different things? Yes? No? Sort of? But they're connected, somehow... right? I mean, I disable my card in one place, but find that billing is still trying to go to it anyway. And then I find another place on another Google page that mentions that card, but when I try to disable it I get some opaque error about "can't disable card because card is already in use. Disable card first" or whatever.
I can't even... I mean, shit. It's hard to imagine creating an experience that is that bad even if you were trying to do so.
Let me just say, I won't be recommending Google's AI API's, or GCP, or Vertex, or any of this stuff to anybody, anytime soon. I don't care how good their models are.
At least chatting with Gemini at gemini.google.com works. So far that's about the only thing AI related from Google I've seen that doesn't seem like a complete cluster-f%@k.
Ha, I have been steeling myself for a long chat with Claude about “how the F to get AI Studio up and working.” With paying being one of the hardest parts.
Without a doubt one essential ingredient will be, “you need a Google Project to do that.” Oh, and it will also definitely require me to Manage My Google Account.
There is an entire business opportunity in just building better user and developer frontends to Google's AI products. It's so incredibly frustrating.
lol that’s our whole company, Nimstrata
As a small advertiser, it can be surprisingly hard to give them money sometimes. (Trying to advertise an Airbnb.)
I ended up using OpenRouter (which I use anyway).
It's amazing that the "hard problems" are turning out to be "not creating a completely broken user experience".
Is that going to need AGI? Or maybe it will always be out of reach of our silicon overlords and require human input.
Same, I couldn't give them my money.
>I decided to link my card to their AI studio.
A lot of us did this in the last 2 days. Gemini3 first and now this.
You should try contacting customer service.
Oh my, you should have tried to integrate with Google Prism. That was a madness! Nano Banana was just a little tricky to set up in comparison!
Try fal.ai instead, it has all image models.
Yeah I was confused. I guess I’ll stick with nano plum for now.
I had to write a post request to try it when it launched
You can use it also in Gemini.
It wasn't there when I first went to Gemini after the announcement, but upon revisiting it gave me the prompt to try Nano Banana Pro. It failed at my niche (rare palm trees).
Incredible technology, don't get me wrong, but still shocked at the cumbersome payment interface and annoyed that enabling Drive is the only way to save.
> at the cumbersome payment interface and annoyed that enabling Drive is the only way to save.
For the general audience, Gemini is the intended product, API and AI studio is for advanced users. Gemini is very easy to pay for. In Gemini, you can save all images as a regular browser download by clicking the top right of the image where it says "Download full size".
I hate that they kinda try to hide the model version. Like if you click the dropdown in the chat box, you can see that "Thinking" means 3 Pro. When you select the "Create images" tool, it doesn't tell you it's using Nano Banana Pro until it actually starts generating the image.
Tell me the model it's using. It's as if Google is trying to unburden me with the knowledge of what model does what but it's just making things more confusing.
Oh, and setting up AI Studio is a mess. First I have to create a project. Then an API key. Then I have to link the API key to the project. Then I have to link the project to the chat session... Come on, Google.
How long till ai studio is in the graveyard i wonder? For real google has some of the most amazing tech but jfc do they suck at making a product.
The only way i use google is via an api key which billing for is arcane to be charitable. How can billions not crack the problem of quickly accepting cash from customers? Surely their ads platform does this?
[dead]