Can't pay for usage?

After this upgrade, I practically hit the usage limits in hours! That said, I used to be able to set the “[Dev] GCP Project ID” in the Antigravity-IDE settings, and even though I lose access to Opus, I would still be able to use it at least. Now, no matter if I set it or not, I cannot get antigravity-ide to just bill me per token. The cli doesn’t have this issue, nor does Antigravity - it correctly says "Your Plan: Antigravity Business" and allows me to pay per token. The IDE did once before but now, on both my machines, that that is no longer an option.

I’m guessing this is a sign that the IDE is being sunsetting, and I don’t know why I am not switching back to VSCode when all the signs are there, but yeah. It would be nice to know whats going on.

Ever since 2.0 is when my credits would disappear in a day, before that, I practically only seen it ONCE and my usage has not changed.

Upgrading my Workspace and adding on the “Expanded AI Access” plan did absolutely nothing for me either.

And I have been waiting MONTHS for Opus 4.6 to be added to my IAM quota. Just an all around fail. We spend thousands of dollars a year and CANT even spend more when we want to.

Hey Moek,

Are you using the original Antigravity IDE software that existed before 2.0 was released? If so, I believe you’re correct, and that version is being retired. But the identical latest version is available here, and has no end in sight. If you updated to this version from the old one, I suggest uninstalling anyway and install this version fresh. Delete the folder in %APPDATA% before you install it. (Antigravity).

I hope that helps!

-Ray

I get the same problem. So I built a proxy for this. You can get it here: GitHub - 12errh/antigravity-proxy: A TypeScript proxy that intercepts Antigravity's Gemini API and routes to NVIDIA or OpenRouter — chat, tools, browser automation, all working. · GitHub . What it does is intercept the Google Antigravity 2.0 request and route it through a custom provider. Currently, I am using it with NVIDIA because it has good models. But you can also use it with OpenRouter or local models.