Totally agree, you described this exactly like it is for me right now, pretty frustrating.
Force a 5 days wait when you’re paying a subscription is plain madness.
There are other providers out there. With great models.
To be clear - I am still with Antigravity, but pairing it up with other tools is never a bad idea.
I tried to trick antigravity with my other email but they all went to rampage for the limit within 15 minutes all gone. Not even new user getting fix limits, specifically talking about Claude opus
I just signed up to AI pro today. Used up opus on first 5 hour window, and then now it tells me I have a 6 day wait…. I think this is really dishonest. Clearly there is some kind of weekly limit. What’s the point of showing the 5 hour usage limit when clearly the weekly limit is the limiting factor?
I have the same issue. Claude models dont reset en 4-5 hours and neither do the Gemini Pro and Low 3.1.
It is really lame from Google to do this, in a silent way, they aren’t even acknowledging it formally.
And the worst part is that they are not going to compensate us for all this lost time.
Thank God we can pay for Claude and just install the addon in VS Code. I wasn’t doing it but they’re forcing everyone to do it. Besides it is way better model.
Same issue. I am a Pro user and was using antigravity heavily, then got like a 100+ hour refresh. Afterwards, I was not using antigravity at all, was using Claude Max through the antigravity extension. Meanwhile antigravity refreshed to 4/5 hours and I still did not use it as Clause max was doing the job better. Then suddenly today I saw there’s almost 7 day (168 hours) refresh! this is wierd!
I got same issue , without exhausting the weekly limits i got shift from 11/3 to 18/3 , this is insane
Hello everyone,
To provide you with greater control and a seamless path to scale, we are evolving our Google AI plans by introducing built-in AI credits that can now be utilized directly within Antigravity.
Under this updated structure, our Google AI Pro tier is tailored for practical builders, offering generous limits for Gemini Flash alongside a baseline quota to experience our most advanced premium models. For developers operating at the highest scale who require consistent, high-volume access to our most complex models, Google AI Ultra serves as the ideal comprehensive solution.
Furthermore, we’ve designed these plans with maximum flexibility in mind; if you are on the Pro plan and require additional capacity or deeper premium access for intensive development sprints, you can seamlessly top up your AI credits to customize your limits and continue shipping your best work without interruption.
Thanks for the clarification on the new Google AI plans.
My issue here is not about needing higher limits or more credits, but about a quota reset timer bug on Pro: after fully consuming my quota over the weekend and waiting until the expected reset time on Thursday at 07:00, the timer jumped from “a few minutes left” to “7 more days of lockout” with no additional usage.
Could someone from the team please:
confirm whether this behavior is actually expected under the new Pro credit model, or
treat it as a bug and manually reset my quota so I can resume my work?
I rely on Antigravity Pro for a multi‑agent research system and my PhD thesis work, so understanding whether this is a bug or the new normal is critical for me to decide whether I should keep investing in Antigravity or start migrating these projects to another IDE that doesn’t randomly turn 5‑hour resets into 7‑day vacations. At this point it honestly feels like the AI backend has quietly unionized and is taking surprise long weekends on my Pro quota.
Is this Model Quota BUG fixed yet? I see no official fix or explanation from Google Devs about this topic. Instead of focusing on development, I end up having to check my model quota limits after every few prompts, worried about the burn rate. But despite all these checks n balances, Model Quota still ends up erratically jumping from 2 Hour reset window to sometimes 4 or 6 days!! Which developer in the right mind would want to wait that long!! I’m talking about PAID GOOGLE AI PRO PLAN. Last night this happened with Gemini 3.1 Pro and I’m stuck with Flash. Other times I’ve seen the same pattern for Claude Opus, which btw also takes down Sonnet and GPT OSS along-with it.
Let’s admit it. This is either a Antigravity BUG which apparently makes it a TOKEN HOG (in addition to being a MEMORY HOG) - OR - the Google AI Pro plan is basically a Gemini Flash plan with preview/teasers of Gemini Pro and Opus models thrown in the mix for marketing, because in all practicality only that’s what we’re getting here. Just couple of prompts with these models before Antigravity/Model loses its mind. I’m OK with this too, really, but at least can we expect Google to show this quota burn rate clearly and reliably on the UI instead of quotas refreshes jumping from 2 hours to 6 days?? How can anyone possibly plan their work like this?
GOOGLE DEVS - PLEASE ACKNOWLEDGE THIS PROBLEM SO THAT WE KNOW A FIX IS IN YOUR ROADMAP INSTEAD OF ECHO CHAMBERS!