Feature Request: Transparent Model Quota & Token Usage Dashboard (Pro Plan)

Google Antigravity
, ,
1

Hi Antigravity Team,

I’m currently using the Google AI Pro plan and working heavily across multiple models, including:

  • Gemini 3 Pro (High)

  • Gemini 3 Pro (Low)

  • Gemini Flash

  • Claude Sonnet 4.5

  • Claude Sonnet 4.5 (Thinking)

  • Claude Opus 4.5 (Thinking)

  • Claude Opus 4.6 (Thinking)

  • GPT-OSS 120B (Medium)

First of all, Antigravity is powerful and extremely useful for development workflows. However, I’m facing a major usability issue regarding quota visibility and refresh behavior.

:warning: Current Problem

In the Pro plan documentation, it states:

image
image1906×961 128 KB

“High, generous quota, refreshed every five hours.”

However, in practice:

  • Sometimes quota refresh behaves as expected.

  • Other times, refresh takes 1–3 days.

  • There is no clear visibility into:

    • Remaining quota per model

    • Token usage

    • Requests used

    • Refresh countdown timer

    • Weekly limit consumption

This makes it difficult to:

  • Plan workloads

  • Choose which model to use

  • Debug quota exhaustion errors

  • Estimate operational limits

I recently received the error:

image
image562×125 4.68 KB

“You have exhausted your quota on this model…”

But there is no way to see:

  • How much I used

  • What the limit actually is

  • When exactly it will reset

:white_check_mark: Feature Request: Usage & Quota Monitoring Dashboard

It would be extremely helpful if Antigravity provided:

:one: Per-Model Quota Dashboard

For each model:

  • Total quota allocation

  • Used quota

  • Remaining quota

  • % usage bar

  • Reset time countdown (live timer)

:two: Token & Request Monitoring

  • Total tokens used (input/output separately)

  • Total requests made

  • Thinking tokens (for thinking models)

  • Daily / 5-hour window usage

  • Weekly usage

:three: Usage Logs

  • Timestamped log of model usage

  • Model name

  • Tokens consumed

  • Status (success / quota exceeded)

  • Filter by date range

:four: Refresh Transparency

If quota is:

  • 5-hour rolling window → show exact reset time

  • Weekly limit → show remaining weekly capacity

  • Dynamically adjusted → clearly mention that in dashboard

:bullseye: Why This Is Important

For Pro users building production-level systems:

  • We need predictable limits.

  • We need visibility.

  • We need planning control.

Right now, quota behavior feels inconsistent and opaque, which affects workflow reliability.

:light_bulb: Suggested UI Example

A simple dashboard page like:

Model Used Limit Remaining Resets In
Gemini 3 Pro (High) 1.2M tokens 2M 800K 02:14:32
Claude Opus 4.6 (Thinking) 450K 500K 50K 1d 04h

Plus:

  • Graph view (last 7 days usage)

  • Export logs option (CSV)

:folded_hands: Request

Please consider adding:

  • A transparent usage tracking panel

  • Clear refresh timing logic

  • Per-model quota breakdown

This would significantly improve developer confidence and workflow planning.

Thank you for building Antigravity — it’s incredibly powerful. With proper quota transparency, it would be even better.

9 Likes
Antigravity: Authenticating
2

Hi @Abhijit_Pramanik,
kindly create this feature request in internal team.

3

There are several extensions in the marketplace addressing this issue. We are using Antigravity Nano.

4

Hi @Yasir_Dev,

Thank you for your valuable feedback. We sincerely appreciate you taking the time to share your thoughts with us, and we’ll be filing a feature request.

2 Likes
5

What you are saying is not exactly true. Plugins like Antigravity Nano show the current consumption per model, but the Gemini Pro models (high and low) have two limits: the short one (5h) and the weekly one. Only the short one is shown. How am I supposed to gauge the current consumption if I don’t know where I am with the weekly consumption? So should we just ‘trust’ it? No sir, I don’t buy it!

1 Like