Skip to main content

Overview

ZeroLimit provides real-time monitoring of your AI provider quotas across multiple accounts and services. The quota monitoring dashboard gives you instant visibility into your usage limits, helping you avoid service interruptions and manage your AI resources effectively.
Quota Monitoring Dashboard

Key Features

Real-Time Tracking

Monitor quota usage across all connected providers with automatic refresh capabilities

Multi-Provider Support

Track quotas for Antigravity, OpenAI Codex, Gemini CLI, Kiro, GitHub Copilot, and Claude

Visual Progress Bars

Color-coded progress indicators show usage levels at a glance

Privacy Controls

Toggle privacy mode to mask sensitive account information

Supported Providers

ZeroLimit monitors quotas for the following AI providers:
  • Antigravity - Claude/GPT, Gemini Pro, Gemini Flash models
  • OpenAI Codex - ChatGPT Plus/Free tier limits
  • Gemini CLI - Google AI quota buckets by project
  • Kiro (CodeWhisperer) - AWS AI coding assistant limits
  • GitHub Copilot - Copilot usage quotas
  • Claude (Anthropic) - Direct Claude API quotas

Using the Quota Dashboard

Viewing Your Quotas

  1. Navigate to the Quota page from the main menu
  2. Ensure you’re connected to the CLI Proxy (see Quickstart)
  3. Your connected accounts will automatically load and display quota information

Provider Filtering

1

Select Provider

Click on any provider tab at the top of the dashboard to filter by that service
2

View Details

The dashboard shows the number of connected accounts for each provider
3

Switch Between Providers

Quickly switch between providers to monitor different services

View Modes

ZeroLimit offers two display modes for your quota data:
List View displays detailed cards with comprehensive quota information:
  • Account email/identifier
  • Provider and filename badges
  • Grouped model quotas (e.g., Claude, Gemini, GPT)
  • Reset time counters
  • Refresh and Details buttons
This view is ideal for in-depth monitoring and analysis.

Understanding Quota Colors

The dashboard uses color coding to indicate quota status:
Your quota is healthy with plenty of usage remaining. No action needed.
Your quota is running low. Consider managing usage or waiting for reset.
Account is temporarily suspended. Check your provider account status.

Quota Card Features

Refresh Individual Quotas

Click the Refresh button on any quota card to update that specific account’s quota information without refreshing all providers.

View Detailed Breakdown

Click the Details button to open a modal showing:
  • Complete list of all models under your account
  • Individual quota percentages for each model
  • Reset times for quota replenishment
  • Organized by model groups (Claude, Gemini Pro, GPT, etc.)
The details modal organizes models into logical groups, making it easy to see which specific AI models have quota remaining.

Privacy Mode

Protect sensitive information during screen sharing:
  1. Click the Eye/Eye-Off toggle in the top-right corner
  2. In privacy mode:
    • Email addresses are masked (e.g., j***@g*****.com)
    • Filenames and folders are partially hidden
  3. Toggle off to show full information

Refresh All Quotas

Use the Refresh All button in the top-right to update quota information for all visible accounts in the current provider tab.
Quota data is automatically fetched when you first load the page. Use manual refresh to get the latest usage information.

Model Grouping

ZeroLimit intelligently groups related models for easier monitoring:
GroupIncludes
ClaudeAll Claude Sonnet, Opus models
Gemini ProGemini 3 Pro, high-capacity models
Gemini FlashGemini 2.5 Flash, Flash Lite, fast models
GPT-4GPT-4, o1 models
GPT-3.5GPT-3.5 Turbo variants

Average Percentage Display

For grouped models, ZeroLimit shows the average quota remaining across all models in that group, giving you a quick health check.

Reset Times

Many providers display quota reset times:
  • Relative times: “in 2 hours”, “in 5 days”
  • Automatic calculation: Based on provider’s reset schedule
  • Per-model resets: Some models reset at different intervals
Plan your usage around reset times to ensure continuous access to AI services.

Empty and Error States

No Credentials

If you haven’t connected any providers yet, you’ll see a prompt to add accounts via the Proxy Management page.

Connection Required

Ensure the CLI Proxy is running and you’re authenticated. See Proxy Management for setup instructions.

Error Messages

If quota fetching fails:
  • Check your internet connection
  • Verify the CLI Proxy is running
  • Ensure account credentials are valid
  • Try refreshing the individual account

Best Practices

1

Monitor Regularly

Check your quotas daily if you’re a heavy AI user
2

Set Up Multiple Accounts

Connect multiple provider accounts for redundancy
3

Watch Reset Times

Note when quotas reset to plan high-usage tasks
4

Use Privacy Mode

Enable privacy mode when presenting or screen sharing

Next Steps

Add Providers

Connect more AI provider accounts

Multi-Provider Support

Learn about supported providers

Build docs developers (and LLMs) love