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!
> I get the feeling GCP is not good for individuals like I.
Google isn't good for individuals at all. Unless you've got a few million followers or get lucky on HN, support is literally non-existent. Anyone that builds a business on Google is nuts.
I'd like to state the AWS, in contrast, has been great to me as an individual. The two times that I needed to speak to a human, I had one on the phone resolving my issue. And both issues were due to me making mistakes - on my small personal account.
Yes, it’s extremely complicated. I gave up on fire base for one project because I could not figure out how to get the right permissions set up and my support request resulted in someone copying and pasting a snippet from the instructions that I obviously had not understood in the first place.
It’s also extremely cumbersome to sign up for Google AI. The other day I tried to get deep seek working via Google’s hosted offering and gave up after about an hour. The form just would not complete without error and there was not a useful message to work with.
It would seem that in today’s modern world of AI assistance, Google could set up one that would help users do the simplest things. Why not just let the agent direct the user to the correct forms and let the user press submit?
Oh man, I've been playing with GCP's vertex AI endpoints, and this is so representative of my experience. It's actually bananas how difficult it is, even compared to other GCP endpoints
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.
Its not a new problem though, and its not just billing. The UI across Gemini just generally sucks (across AI Studio and the chat interfaces) and there's lots of annoying failure cases where Gemini will just timeout and stop working entirely midrequest.
Been like this for quite a while, well before Gemini 3.
So far I continue to put up with it because I find the model to be the best commercial option for my usage, but its amazing how bad modern Google is at just basic web app UX and infrastructure when they were the gold standard for such for like, arguably decades prior.
We are talking here about the most basic things- nothing AI related. Basic billing. The fact that it is not working says a lot about the future of the product and company culture in general (obviously they are not product-oriented)
Given how many paid offerings Google has, and the complexity and nuance to some of those offering (e.g. AdSense) I am pretty surprised that Google don't have a functioning drop in solution for billing across the company.
If they do, it's failing here. The idea of a penny pinching megacorp like Google failing technically even in the penny pinching arena is a surprise to me.
Even though my post complaining about google's billing and incoherent mess got so many upvotes, I'll be the first to say that there is nothing basic about "give me money".
Apart from the fact that what happens to the money when it gets to google (putting it in the right accounts, in the right business, categorizing it, etc), it changes depending on who you're ASKING for money.
1. Getting money from an individual is easy. Here's a credit card page.
2. Getting money from a small business is slightly more complicated. You may already have an existing subscription (google workspaces), just attach to it.
3. As your customers get bigger, it gets more squishy. Then you have enterprise agreements, where it becomes a whole big mess. There are special prices, volume discounts, all that stuff. And then invoice billing.
The point is that yes, we all agree that getting someone to plop down a credit card is easy. Which is why Anthropic and OpenAI (who didn't have 20 years of enterprise billing bloat) were able to start with the simplest use case and work their way slowly up.
But I AM sensitive to how hard this is for companies as large and varied as Google or MS. Remember the famous Bill Gates email where even he couldn't figure out how to download something from Microsoft's website.
It's just that they are also LARGE companies, they have the resources to solve these problems, just don't seem to have the strong leadership to bop everyone on the head until they make the billing simple.
And my guess is also that consumers are such a small part of how they're making money (you best believe that these models are probably beautifully integrated into the cloud accounts so you can start paying them from day one).
My first thought was this is the whole thing about managers at Google trying to get employees under other managers fired and their own reports promoted -- but it feels too similar to how fucked up all the account and billing stuff is at Microsoft. This is what happens when you try to "fix" something by layering on more complexity and exceptions.
From past experience, the advertising side of the business was very clear with accounts and billing. GCP was a whole other story. The entire thing was poorly designed, very confusing, a total mess. You really needed some justification to be using it over almost everything else (like some Google service which had to go through GCP.) It's kind of like an anti-sales team where you buy one thing because you have to and know you never want to touch anything from the brand ever again.
We made the bet 2 years ago to build AI Studio on top of the Google Cloud infra. One of the real challenges is that Google is extremely global, we support devs in hundreds of countries with dozens of different billing methods and the like. I wish the problem space was simple but on the first day I joined Google we kicked off the efforts to make sure we could bring billing into AI Studio, so January cannot come soon enough : )
No one should even notice the payment flow. This isn't Stripe where the polish on the payment experience is a selling point for the service. At Google, paying for something should be a boring but quick process that works and then gets out of the way.
It doesn't need to be good. It just need to be not broken.
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.
A company with a literal embedded payment processor, including subscription services for half of all mobile users can't manage to take payments for their own public facing services seems like a huge fucking failure to me.
Especially for software developer and tech influencer focused markets.
Considering the product itself seems to be excessively limited without actually getting paid for it, and the paid tier itself having so many onboarding issues, as a critical usage path, it's pretty bad.
This is in a $3.6 Trillion company, for a product they're spending billions a quarter to develop, with specialized employees making mid 6-figure to 7-figure salaries and bonuses... you'd think somebody has the right connections into the departments that typically handle the payment systems.
My expectations shoot up dramatically for organizations that have all the funding they need to create something "insanely great" in terms of user experience the further they fall short... I don't know who the head of this group/project/department/product is... but someone failed at their job, and got payed excessively for this poor execution.
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.
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!
Thank you for your service. Also, one of the main issues from the outside seems to me to be the impedance mismatch between google's entire cloud business and the direct-to-dev type API access oAI and Anthropic have pioneered. So, there's always going to be some pain here. It would be realllyy nice if that pain were incurred internally at the mothership, both for Dev UX and for sales. But so far, it looks to me like it's being spread out internally and externally.
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.
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.
Since 3 days I am trying to get a login to Antigravity and first there was trouble with an api now all I get is 'Your current account is not eligible for Antigravity. Try signing in with another personal Google account'. Even though it is verified and in a supported region...
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.
We use Google Cloud's billing service, but given the super global nature of our customer base, there is a lot of complexity in moving this into AI Studio. Though we are making great progress!
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?
The permission thing happens to me too, but very intermittently, usually a couple of hard refreshes of the tab clears it up, sometimes I need to delete the conversation I'd just tried to start and start a new conversation. I can't remember the exact message, sometime like you don't have permission or permission denied. If I had to guess it happens 1 in 5 sessions I load. The API key stuff would be a lot easier if it landed you on the correct page in the GCP portal when it directs you out of AI studio, I think that is the most confusing part of the experience, you end up on what seems like a random GCP billing page with no clear indication as to what it has to do with API keys.
Pls email me if you can on the latter, we can update whatever pointers we have to the cloud console and make them more contextual. We are also pushing on the north star of the P99 user experience not needing to leave AI Studio. We have landed a lot of stuff to make this possible already!
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.
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?
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.
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.
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?
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…
Don't forget the tradition of having to migrate to a new API after a while because this one gets deprecated for "reasons". Not just a newer version, but a complete non backwards compatible new API that also requires its own setup.
To be fair, that might have changed in recent years. But after having to deal with that a few times for a few hobby projects I simply stopped trying. Can't imagine how it is for companies making use of these APIs. I guess it provides work for teams on otherwise stable applications...
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?
I know not accessible across all API's, but the point of AI Studio is you can sign up and we just make an API key for you automagically, no extra button clicks or the like.
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.
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.
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.)
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.
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.
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:
They also offer (multiple; confusing product lineup!) interactive apps for upscaling video on their own website - Topaz Video and Astra. And maybe more, who knows.
I have access to the interactive apps, and there are a lot of knobs that aren't exposed in the Fal API.
edit: lol I found a third offering on the Topaz site for this, "Video upscale" within the Express app. I have no idea which is the best, despite apparently having a subscription to all of them.
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?
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.
This is a good point. Some of the tools have a "creative mode" or "creativity" knob that hopefully drives this point home. But the simpler ones don't, and even with that setting dialed back it still has the same fundamental limitations/risks.
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.
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.
For new users in AI Studio, we make a cloud project and key for you automatically. Hear you on the billing setup, we are working on it, landing in January!
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?
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-