Configure pay-as-you-go usage above quota

When your project reaches its pooled quota for a feature in Gemini Enterprise, feature usage stops unless you turn on pay-as-you-go usage above quota. Turning on pay-as-you-go usage above quota (formerly referred to as overages) lets users in your project continue using features beyond the included pooled quota limits at pay-as-you-go rates.

To turn on pay-as-you-go usage above quota, your project needs at least one active, non-free-trial subscription for one of the following product editions:

  • Gemini Enterprise Standard
  • Gemini Enterprise Plus
  • Gemini Enterprise Frontline Starter and Frontline Worker
  • Gemini Enterprise EDU and EDU Pro
  • Gemini Enterprise Standard Emerging Market, Emerging Market EDU, Emerging Market governments. Emerging market editions are available only to eligible customers. Your Google account team assesses the requirements to determine your eligibility.

To learn how pricing works and view the pricing tables for each feature, see Quotas and pay-as-you-go usage.

Key concepts

This section introduces key billing concepts for pay-as-you-go usage above quota in Gemini Enterprise.
Term Definition
Pooled quota The usage included with your licenses. Each license adds to a quota for each feature that all users in the edition share. For more information, see Quotas and pay-as-you-go usage.
Pay-as-you-go usage above quota A setting that lets usage continue after the pooled quota runs out. This usage is charged at pay-as-you-go rates.
Project monthly spend limit A Cloud Billing budget cap that stops paid usage when your project reaches the amount that you set.
Billing account type Determines how you pay for usage:
  • A self-serve (online) account pays with prepaid credits.
  • An invoiced account pays on its monthly invoice.
To check your account type, see Find out your Cloud Billing account type and charging cycle.
Prepaid credits Credits that a self-serve billing account buys in advance. Paid usage is deducted from the credit balance. When you turn on pay-as-you-go usage above quota for the first time, you can continue with a zero balance. If your balance is zero, usage above quota stops until you add credits. If prepaid credits are already set up and your balance is zero, you must add credits before turning it on again. To use the Pay-as-you-go edition, you must buy credits when setting up prepaid credits on your billing account. For more information, see Manage prepaid credits.

Before you begin

You can configure pay-as-you-go usage above quota and set spend limits if you meet the following requirements:

  • You have the Gemini Enterprise Admin (roles/discoveryengine.agentspaceAdmin) role on the project.

  • You have at least one active, non-free-trial Gemini Enterprise subscription for a license-based edition (such as Gemini Enterprise Standard, Plus, Frontline, EDU, or Emerging Market editions).

  • Your project is linked to a Cloud Billing account that's in good standing. To check your billing account type, see Find out your Cloud Billing account type and charging cycle.

  • To turn on pay-as-you-go usage above quota for the first time with a self-serve billing account, you need the Billing Account Administrator (roles/billing.admin) role on the billing account. This step sets up the prepaid credit balance. Without this role, the Google Cloud console shows You do not have billing admin access.

Turn on pay-as-you-go usage above quota

To turn on pay-as-you-go usage above quota for a subscription tier, follow these steps:

  1. In the Google Cloud console, go to the Gemini Enterprise > Usage & spend page.

    Go to Usage & spend

  2. Select the Usage tab.

  3. In the tier selector banner at the top of the page, select the subscription tier you want to configure:

    • Standard
    • Plus
    • Frontline Starter
    • Frontline Worker
    • EDU
    • EDU Pro
    • Standard Emerging
    • EDU Emerging
    • EDU Pro Emerging
    • EDU Gov Emerging

  4. In the Feature usage section, locate the Pay-as-you-go usage above quota card.

  5. In the Status column, turn on the toggle (Enabled).

  6. In the PayGo Option column, select your pay-as-you-go option:

    • Standard: Default pay-as-you-go throughput.
    • Priority: Priority pay-as-you-go provides more consistent performance than Standard PayGo without the upfront commitment of Provisioned Throughput. Priority PayGo is available only when your application location is set to global.

  7. Click Save changes.

  8. Complete the dialog that appears:

    • Self-serve billing account (with billing permissions): In the Your current credit balance dialog, click Add credits to buy credits, or click Continue to use your current balance.
    • Invoiced billing account (or self-serve without billing permissions): In the Overage enabled dialog, click Got it.

Set a monthly spend limit

You can set a monthly spend limit on pay-as-you-go usage above quota and Pay-as-you-go edition usage for your project. When your project reaches this limit, Gemini Enterprise automatically stops usage beyond quota to prevent unexpected charges. Usage resumes at the start of the next month, or earlier if you lift the spend cap.

If you pay with prepaid credits, the spend limit still applies. Usage stops when your project reaches the spend limit or your credit balance reaches zero, whichever happens first.

The budget you set applies to the following product areas:

  • Gemini Enterprise app
  • Gemini Enterprise Agent Platform
  • AI developer tools such as Google Antigravity

To configure a monthly spend limit, do the following:

  1. In the Google Cloud console, go to the Gemini Enterprise > Usage & spend page.

    Go to Usage & spend

  2. Select the Usage tab.

  3. In the Project monthly spend limit section, click Set limit.

  4. In Cloud Billing, configure your budget and spend cap actions. When defining the scope of your budget, select Vertex AI (aiplatform.googleapis.com) from the Services list. Cloud Billing bills pay-as-you-go charges for Gemini Enterprise and AI developer tools under Vertex AI API.

    For more information about creating budgets and configuring spend limits, see Set budget spend caps.

Turn off pay-as-you-go usage above quota

When you turn off pay-as-you-go usage above quota, feature usage stops after your project reaches its pooled quota limits for that tier.

If you pay with prepaid credits, your remaining credits stay in your balance until they expire, and you can use them if you turn pay-as-you-go usage above quota on again. Because billing data can take some time to process, you might be charged for some usage after you turn it off.

To turn off pay-as-you-go usage above quota for a subscription tier, follow these steps:

  1. In the Google Cloud console, go to the Gemini Enterprise > Usage & spend page.

    Go to Usage & spend

  2. Select the Usage tab.

  3. In the tier selector banner at the top of the page, select the subscription tier where you want to turn off pay-as-you-go usage.

  4. In the Feature usage section, locate the Pay-as-you-go usage above quota card.

  5. In the Status column, turn off the toggle (Disabled).

  6. Click Save changes.

  7. In the Disable overage? dialog, click Disable overage.

Configure a single-user quota limit

To prevent any individual user from exhausting an edition's included subscription quota pool before other users can access it, you can configure a single-user quota limit in the Feature usage > Limit any single-user's quota section on the Usage & spend > Usage tab.

Single-user quota limits apply only while your edition's subscription quota pool has remaining capacity; they don't limit pay-as-you-go usage above quota after the subscription pool is depleted. For more information, see the following:

What's next