> [!NOTE]
> **Note:** The quotas and pay-as-you-go usage above quota on this page don't apply to users who received the email with the subject line *\[Billing Update\] New Gemini Enterprise
> overage billing controls launching August 17, 2026* . If you received this email, see [Quotas and overages (Legacy)](https://docs.cloud.google.com/gemini/enterprise/docs/overages.md.txt).

Your subscription entitles you to certain quotas across product features. If you
have a pay-as-you-go subscription, there are no feature quota limits; you pay
for what you use. For seat-based subscriptions, unlike other Google Cloud
services, Gemini Enterprise feature quotas don't require manual increase
requests; they're automatically adjusted based on the number of licenses or
seats in your subscription, including free-trial subscriptions.

> [!NOTE]
> **Note:** Google Cloud products that use the Discovery Engine API, including Agent Search and Gemini Enterprise, share the technical rate and allocation quotas listed on this page. However, license-based feature quotas apply only to Gemini Enterprise and aren't shared with Agent Search.

> [!NOTE]
> **Note:** As a Discovery Engine administrator, you can view pooled quota usage. For more information, see [View the pooled quota usage](https://docs.cloud.google.com/gemini/enterprise/docs/feature-usage.md.txt#view-quota-usage).

## Feature and edition-based quotas

Except for storage and data indexing, feature quotas are pooled across users in
the same edition within a project and location. Storage and data indexing quota
is pooled per project and location across all users, but it isn't segmented by
the edition---all editions share a single storage and data indexing pool. For all
other feature quotas, users with licenses for a specific edition share a single
combined limit per project and location.

For detailed system limits, subagent depth constraints, file upload thresholds, and sharing member caps that apply to custom agents, see [Workflow Builder quotas and limits](https://docs.cloud.google.com/gemini/enterprise/docs/workflow-builder/quotas-and-limits.md.txt).

#### Use case 1: Multiple editions in one project and location

If you have users with different editions in the same project and location,
quota pools are maintained separately for each edition except for storage and
data indexing:

- **Standard feature quotas:** Quotas are pooled separately by edition in each project and location. For example, if a project and location has 100 Standard edition licenses and 50 Plus edition licenses, your Standard edition users share a pool of 16,000 Assistant queries per day (100 licenses × 160 queries), and your Plus edition users share a separate pool of 10,000 queries per day (50 licenses × 200 queries). These feature quota pools don't combine across editions.
- **Storage and data indexing:** Quotas are pooled per project and location across all users, regardless of edition. For example, if a project and location has 100 Standard edition licenses (30 GiB per user) and 50 Plus edition licenses (75 GiB per user), there is a single combined storage pool of 6,750 GiB ((100 × 30 GiB) + (50 × 75 GiB)) shared by all users in that project and location across all editions.

#### Use case 2: Quota pooling within a single edition

Within an edition's quota pool, the following rules apply. For example, if you
have 10 Standard edition licenses, your users share a total pooled quota of
1,600 queries per day (10 licenses × 160 queries):

- The 10 Standard edition users share a combined pool of 1,600 queries for the day.
- One power user can use 500 queries, leaving 1,100 queries for the remaining users in that edition.
- By default, users share a single pool of quota for the edition. To restrict individual quota usage, an administrator must configure a [single-user quota limit](https://docs.cloud.google.com/gemini/enterprise/docs/quotas-and-pay-as-you-go-usage.md.txt#single-user-quota-limits).

### Single-user quota limits

By default, all users share the edition's quota pool without individual
limits. To restrict consumption per user, turn on the **Limit any
single-user's quota** setting on the **Usage \& spend \> Usage** page in the
Google Cloud console.

> [!NOTE]
> **Note:** The multiplier also applies to AI developer tools, including Google Antigravity. For AI developer tools, the limit applies to the weekly quota. Each user's limit resets seven days after the start of that user's cycle, which can differ from the pool's reset.

For more information, see
[Configure a single-user quota limit](https://docs.cloud.google.com/gemini/enterprise/docs/feature-usage.md.txt#configure-single-user-quota-limit).

When you configure a single-user quota limit, the following rules apply:

- **Supported editions**: You can configure single-user quota limits for Gemini Enterprise Standard, Gemini Enterprise Plus, and Gemini Enterprise Standard Emerging Market editions. However, the single-user quota limit for AI developer tools doesn't apply to the Gemini Enterprise Standard Emerging Market edition.
- **Per-edition and per-location configuration:** When you enable the limit,
  you can set a **Multiplier** (a whole number of 1 or greater) for each
  edition and location. If you don't specify a value, the multiplier
  defaults to 10.

  Gemini Enterprise calculates a user's maximum quota usage for a
  feature by multiplying the edition's per-user quota for that feature by
  the multiplier. This limit applies to all users in the specified edition
  and location; you can't customize it for individual users.
- **Uniform across features:** The multiplier applies uniformly across the
  following pooled subscription features within that edition and location:

  - Assistant queries
  - No-code agent building tools
  - Video generation, except in the Standard Emerging Market edition where video generation is pay-as-you-go usage above quota only
  - Image generation, except in the Standard Emerging Market edition where image generation is pay-as-you-go usage above quota only
  - Deep Research
  - AI developer tools, except in the Standard Emerging Market edition

  Quota limits are tracked and enforced independently for each feature. If a
  user reaches their single-user quota limit for one feature, such as image
  generation, they can still use other features, such as Assistant queries.
- **What counts toward a user's limit**: For AI developer tools, usage
  counts toward single-user quota limits as follows:

  - Usage across the Antigravity app, Antigravity CLI, and Antigravity for IDEs counts toward a user's limit.
  - Usage by an agent acting on a user's behalf counts toward the limit of the agent's owner.
  - A service account with an assigned license has its own single-user quota limit.
- **Examples**: The following examples show how a single-user quota limit
  applies to daily and weekly quotas:

  - **Daily feature quotas**: Your project and location have 100 Gemini Enterprise Standard edition licenses. Each license provides a quota of 160 Assistant queries per day and 5 images per day, creating a total shared pool of 16,000 queries and 500 images per day. If you set a 5x multiplier, each user can consume up to 800 Assistant queries per day (5 × 160) and 25 images per day (5 × 5) from the shared pool. If a user reaches their limit of 25 images for the day, they can still use up to 800 Assistant queries and other features.
  - **Weekly AI developer tools quota** : Your project and location have 100 Gemini Enterprise Standard edition licenses. If each license includes <var translate="no">X</var> per week in AI developer tools quota, these licenses create a shared weekly pool of 100<var translate="no">X</var>. If you set a 5x multiplier, each user can consume up to 5<var translate="no">X</var> per week. That usage also counts against the shared pool, so if the pool runs out first, the user can be stopped earlier. For more information, see [How single-user quota limits interact with pay-as-you-go usage above
    quota](https://docs.cloud.google.com/gemini/enterprise/docs/quotas-and-pay-as-you-go-usage#single-user-limits-and-pay-as-you-go).

#### How single-user quota limits interact with pay-as-you-go usage above quota

Single-user quota limits apply only to the subscription quota pool. They don't
restrict pay-as-you-go usage above quota:

- **When the edition's pooled quota has remaining capacity:** If an individual
  user reaches their single-user quota limit for a feature,
  Gemini Enterprise restricts usage of that feature for that user until
  the quota resets (or until the edition's pooled quota for that feature is
  depleted if **Pay-as-you-go usage above quota** is enabled). The user can
  continue using other features that haven't reached their limit, and other
  users in the edition can continue using the remaining pooled quota.

- **When the edition's pooled quota is depleted:**

  - If **Pay-as-you-go usage above quota** is enabled for the edition, the single-user quota limit no longer restricts usage. All users in the edition, including users who previously reached their single-user limit, can continue using the feature at pay-as-you-go rates, up to any configured project monthly spend limit.
  - If **Pay-as-you-go usage above quota** is disabled for the edition, feature usage stops for all users in that edition until the pooled quota resets.

### Quota reset times

Pooled quotas reset on the following schedule:

<br />

| Feature | Reset schedule |
|---|---|
| All features except AI developer tools | Daily at midnight Pacific Time (PT) |
| [AI developer tools](https://docs.cloud.google.com/gemini/enterprise/docs/ai-developer-tools-overview.md.txt) | Every seven days, starting from when a prompt or request is first sent to an AI developer tool. <br /> For example, if a user in your project sends the first prompt using Antigravity on Wednesday at 2 PM Pacific Time (PT), the seven-day quota cycle starts at that time, and the AI developer tools quota resets the following Wednesday at 2 PM PT. |

<br />

### Quotas for Standard and Plus editions

> [!NOTE]
> **Note:** When your project reaches its pooled feature quota for Standard or Plus editions, you can [turn on pay-as-you-go usage above quota](https://docs.cloud.google.com/gemini/enterprise/docs/quotas-and-pay-as-you-go-usage.md.txt#pay-as-you-go-usage-above-quota) to allow uninterrupted usage at pay-as-you-go rates.

For information about quotas across Gemini Enterprise Standard and Plus editions,
see the following table:

|   || Gemini Enterprise Standard | Gemini Enterprise Plus |
| Quotas | Pooled or unpooled | Pooled across users within the edition per project and location | Pooled across users within the edition per project and location |
| Product | Storage + data indexing | 30 GiB | 75 GiB |
| Product |
| Product |
| Product |
| Product |
| Product |
|---|---|---|---|
| Assistant | 160 queries per day | 200 queries per day |
| No-code agent building tools - create^4^ | 1 agent per day | 10 agents per day |
| No-Code agent building tools - use | Based on underlying agent actions^4^ ||
| Video generation | 2 video generation requests per day | 3 video generation requests per day |
| Image generation | 5 images per day | 10 images per day |
| Gemini Notebook - create \& publish | Gemini Notebook for business limits^1^ | Gemini Notebook for business limits^1^ |
| Deep Research | 3 per day | 10 per day |

^1^ For information about Gemini Notebook for business usage limits,
see the
[Gemini Notebook for business documentation](https://docs.cloud.google.com/gemini/enterprise/notebooklm-enterprise/docs/overview.md.txt#usage-limits).

^2^ AI developer tools are available with upgraded self-serve
(online) and invoiced
[Cloud Billing accounts](https://docs.cloud.google.com/billing/docs/concepts.md.txt#billing_account_types),
or with a [billing subaccount](https://docs.cloud.google.com/billing/docs/concepts.md.txt#subaccounts) of an
invoiced billing account. Free-trial subscriptions include AI developer tools,
with a limited quota, only if your project is linked to an invoiced billing
account. For more information, see
[Do free-trial licenses include the AI developer tools quota?](https://docs.cloud.google.com/gemini/enterprise/docs/licenses-faqs.md.txt#free-trial-ai-developer-tools-quota)

^3^ Although quotas are listed as a monthly per-user amount,
Gemini Enterprise enforces them on a rolling seven-day basis as a shared
pool. Gemini Enterprise calculates your project's weekly quota by dividing
the monthly per-user value by four and multiplying it by your project's total
licensed seats, including free-trial seats. Any user in your edition can draw
from this shared weekly pool. Unused quota doesn't roll over to the next week.

^4^ Daily creation quotas apply to both creating custom agents in Workflow Builder and registering external or custom agents (such as A2A, Agent Development Kit (ADK), or Dialogflow agents) in an app. Each registration in an engine or app consumes 1 creation quota unit. For detailed agent creation limits, registration quotas across multi-app architectures, subagent depth constraints, file upload thresholds, and sharing member caps, see [Workflow Builder quotas and limits](https://docs.cloud.google.com/gemini/enterprise/docs/workflow-builder/quotas-and-limits.md.txt#creation-quotas).

### Quotas and pricing for the Pay-as-you-go edition

> [!NOTE]
> **Note** : If your project is linked to a self-serve (online)
> Cloud Billing account, you pay for Gemini Enterprise Pay-as-you-go usage
> with [prepaid
> credits](https://docs.cloud.google.com/gemini/enterprise/docs/manage-prepaid-credits), and if prepaid credits aren't set up on your billing account
> yet, you must buy credits to subscribe. If your project is linked to an
> [invoiced
> Cloud Billing account](https://docs.cloud.google.com/billing/docs/concepts#billing_account_types), usage is billed on your monthly
> invoice.

The Gemini Enterprise Pay-as-you-go edition has no subscription or license
fee and no feature quota limits, because you pay only for what you use at
pay-as-you-go rates. To get started,
[subscribe to the Pay-as-you-go edition](https://docs.cloud.google.com/gemini/enterprise/docs/licenses.md.txt#get-subscription).
For more information about subscriptions, see
[Get subscriptions and assign licenses](https://docs.cloud.google.com/gemini/enterprise/docs/licenses.md.txt#about-subscriptions).

The following table lists the rates and pricing for this
edition:

#### Pay-as-you-go charges for features

Prices are listed in US Dollars (USD). If you pay in a currency other than USD,
the prices listed in your currency on
[Cloud Platform SKUs](https://cloud.google.com/skus/) apply. Charges are
subject to a variable support fee depending on the support service. For more
information on the support services, see
[Compare support services](https://docs.cloud.google.com/support/docs/overview.md.txt#compare-support).

|   || Gemini Enterprise Pay-as-you-go charges |
| Foundational engagement layer | Storage + data indexing | $5 per GiB per month |
| Foundational engagement layer |
| Foundational engagement layer |
| Foundational engagement layer |
| Foundational engagement layer |
| Foundational engagement layer |
| Foundational engagement layer |
|---|---|---|
| Assistant - Gemini models | [Agent Platform prices](https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#cost-of-building-and-deploying-ai-models-in-agent-platform) |
| Assistant - Claude models | [Claude pricing](https://docs.cloud.google.com/gemini/enterprise/docs/quotas-and-pay-as-you-go-usage.md.txt#claude-pricing-pay-as-you-go) |
| No-code agent building tools - create | n/a |
| No-code agent building tools - use | [Agent Platform prices](https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#cost-of-building-and-deploying-ai-models-in-agent-platform) |
| Video generation | [Agent Platform prices](https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#cost-of-building-and-deploying-ai-models-in-agent-platform) |
| Image generation | [Agent Platform prices](https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#cost-of-building-and-deploying-ai-models-in-agent-platform) |
| Claude models | [Claude pricing](https://docs.cloud.google.com/gemini/enterprise/docs/quotas-and-pay-as-you-go-usage.md.txt#claude-pricing-pay-as-you-go) |

^1^ AI developer tools are
available with upgraded self-serve (online) and invoiced
[Cloud Billing accounts](https://docs.cloud.google.com/billing/docs/concepts.md.txt#billing_account_types), or
with a [billing subaccount](https://docs.cloud.google.com/billing/docs/concepts.md.txt#subaccounts) of an invoiced
billing account. Free-trial subscriptions include AI developer tools, with a
limited quota, only if your project is linked to an invoiced billing account.
For more information, see
[Do free-trial licenses include the AI developer tools quota?](https://docs.cloud.google.com/gemini/enterprise/docs/licenses-faqs.md.txt#free-trial-ai-developer-tools-quota)

#### Claude pricing

Pay-as-you-go charges for Claude models apply as defined in the following table:

> [!NOTE]
> **Note:** Claude model pricing and discounts in the Gemini Enterprise app are distinct from pricing procured through Google Cloud Marketplace.

### Global

| Model | Type | Model price (/1M tokens) =\< 200K input tokens | Model price (/1M tokens) \> 200K input tokens |
| Claude Opus 5.5 | Input | $4.00 | $4.00 |
| Claude Opus 5.5 |
| Claude Opus 5.5 |
| Claude Opus 5.5 |
| Claude Opus 5.5 |
|---|---|---|---|
| Output | $20.00 | $20.00 |
| 5m Cache Write | $5.00 | $5.00 |
| 1h Cache Write | $8.00 | $8.00 |
| Cache Hit | $0.20 | $0.20 |
| Output | $10.00 | $10.00 |
| 5m Cache Write | $2.50 | $2.50 |
| 1h Cache Write | $4.00 | $4.00 |
| Cache Hit | $0.20 | $0.20 |

### US Multi-Region (US)

| Model | Type | Model price (/1M tokens) =\< 200K input tokens | Model price (/1M tokens) \> 200K input tokens |
| Claude Opus 5.5 | Input | $4.40 | $4.40 |
| Claude Opus 5.5 |
| Claude Opus 5.5 |
| Claude Opus 5.5 |
| Claude Opus 5.5 |
|---|---|---|---|
| Output | $22.00 | $22.00 |
| 5m Cache Write | $5.50 | $5.50 |
| 1h Cache Write | $8.80 | $8.80 |
| Cache Hit | $0.22 | $0.22 |
| Output | $11.00 | $11.00 |
| 5m Cache Write | $2.75 | $2.75 |
| 1h Cache Write | $4.40 | $4.40 |
| Cache Hit | $0.22 | $0.22 |

### EU Multi-Region (EU)

| Model | Type | Model price (/1M tokens) =\< 200K input tokens | Model price (/1M tokens) \> 200K input tokens |
| Claude Opus 5.5 | Input | $4.40 | $4.40 |
| Claude Opus 5.5 |
| Claude Opus 5.5 |
| Claude Opus 5.5 |
| Claude Opus 5.5 |
|---|---|---|---|
| Output | $22.00 | $22.00 |
| 5m Cache Write | $5.50 | $5.50 |
| 1h Cache Write | $8.80 | $8.80 |
| Cache Hit | $0.22 | $0.22 |
| Output | $11.00 | $11.00 |
| 5m Cache Write | $2.75 | $2.75 |
| 1h Cache Write | $4.40 | $4.40 |
| Cache Hit | $0.22 | $0.22 |

### Quotas for EDU and EDU Pro editions

> [!NOTE]
> **Note:** When your project reaches its pooled feature quota for EDU or EDU Pro editions, you can [turn on pay-as-you-go usage above quota](https://docs.cloud.google.com/gemini/enterprise/docs/quotas-and-pay-as-you-go-usage.md.txt#pay-as-you-go-usage-above-quota) to allow uninterrupted usage at pay-as-you-go rates.

For information about quotas across Gemini Enterprise EDU and EDU Pro editions,
see the following table:

|   || Gemini Enterprise EDU | Gemini Enterprise EDU Pro |
| Quotas (Pooled or Unpooled) || Pooled across users within the edition per project and location | Pooled across users within the edition per project and location |
| Product | Storage + data indexing | 5 GiB | 50 GiB |
| Product |
| Product |
| Product |
| Product |
| Product |
|---|---|---|---|
| Assistant^2^ | 40 queries per day | 200 queries per day |
| No-code agent building tools - Create | 1 agent per day | 10 agents per day |
| No-Code agent building tools - use | Based on underlying agent actions ||
| Video generation | 1 video generation requests per day | 3 video generation requests per day |
| Image generation | 2 images per day | 10 images per day |
| Gemini Notebook - create \& publish | Gemini Notebook for business limits^1^ | Gemini Notebook for business limits^1^ |
| Deep Research | 1 per day | 10 per day |

^1^ For information about Gemini Notebook for business usage limits,
see the
[Gemini Notebook for business documentation](https://docs.cloud.google.com/gemini/enterprise/notebooklm-enterprise/docs/overview.md.txt#usage-limits).

^2^ This includes the usage of Google Search and Web Grounding.

### Quotas for Frontline editions

> [!NOTE]
> **Note:** When your project reaches its pooled feature quota for Frontline editions, you can [turn on pay-as-you-go usage above quota](https://docs.cloud.google.com/gemini/enterprise/docs/quotas-and-pay-as-you-go-usage.md.txt#pay-as-you-go-usage-above-quota) to allow uninterrupted usage at pay-as-you-go rates.

For information about quotas across Gemini Enterprise Frontline Starter and
Worker, see the following table:

|   || Gemini Enterprise Frontline Starter | Gemini Enterprise Frontline Worker |
| Quotas (Pooled or Unpooled) || Pooled across users within the edition per project and location | Pooled across users within the edition per project and location |
| Product | Storage + data indexing | 2 GiB | 2 GiB |
| Product |
| Product |
| Product |
| Product |
| Product |
| Product |
|---|---|---|---|
| Search | Abuse preventative only^2^ |   |
| Assistant | 20 queries per day | 40 queries per day |
| No-code agent building tools - create | n/a | n/a |
| No-Code agent building tools - use | Based on underlying agent actions ||
| Video generation | n/a | 1 video generation request per day |
| Image generation | n/a | 2 images per day |
| Gemini Notebook - create \& publish | n/a | n/a |
| Deep Research | n/a | 1 per day |

^1^ For information about Gemini Notebook for business usage limits,
see the
[Gemini Notebook for business documentation](https://docs.cloud.google.com/gemini/enterprise/notebooklm-enterprise/docs/overview.md.txt#usage-limits).

^2^Subject to abuse-preventative usage limits only.

### Quotas for Emerging Market editions

> [!NOTE]
> **Note:** When your project reaches its pooled feature quota for Emerging Market editions, you can [turn on pay-as-you-go usage above quota](https://docs.cloud.google.com/gemini/enterprise/docs/quotas-and-pay-as-you-go-usage.md.txt#pay-as-you-go-usage-above-quota) to allow uninterrupted usage at pay-as-you-go rates.

For information about quotas across Gemini Enterprise Emerging Market
editions, see the following table:

|   || Gemini Enterprise Standard Emerging Market | Gemini Enterprise Emerging Market EDU and governments |
| Quotas (Pooled or Unpooled) || Pooled across users within the edition per project and location | Pooled across users within the edition per project and location |
| Product | Storage + data indexing | 10 GiB | 3 GiB |
| Product |
| Product |
| Product |
| Product |
| Product |
| Product |
|---|---|---|---|
| Search | Abuse preventative only^2^ | 5 queries per day |
| Assistant | 40 queries per day | 5 queries per day, individual only |
| No-code agent building tools - create | 1 agent per day | 1 agent per day |
| No-Code agent building tools - use | Based on underlying agent actions ||
| Video generation | n/a | n/a |
| Image generation | n/a | 1 image per day |
| Gemini Notebook - create \& publish | Gemini Notebook for business limits^1^ | n/a |
| Deep Research | 1 per day | n/a |

^1^ For information about Gemini Notebook for business usage limits,
see the
[Gemini Notebook for business documentation](https://docs.cloud.google.com/gemini/enterprise/notebooklm-enterprise/docs/overview.md.txt#usage-limits).

^2^Subject to abuse-preventative usage limits only.

^3^AI developer tools don't include bundled quota in the Standard
Emerging Market edition.

## API and system quotas

This section lists the technical infrastructure quotas and system limits for
Discovery Engine API resources used by Gemini Enterprise. System limits
are fixed values that cannot be changed.

### Allocation quotas

The following table lists the allocation quotas for Discovery Engine API.
These quotas don't reset over time. Instead, they're released when you
release the resource.

Google Cloud uses quotas to help maintain fairness and reduce
spikes in resource use and availability. A quota restricts how much of a
Google Cloud resource your Google Cloud project can use. Quotas
apply to a range of resource types, including hardware, software, and network
components. For example, quotas can restrict the number of API calls to a
service, the number of load balancers used concurrently by your project, or the
number of projects that you can create. Quotas protect the community of
Google Cloud users by preventing the overloading of services. Quotas also
help you to manage your own Google Cloud resources.

The Cloud Quotas system does the following:

- Monitors your consumption of Google Cloud products and services
- Restricts your consumption of those resources
- Provides a way to [request changes to the quota value](https://docs.cloud.google.com/docs/quotas/help/request_increase) and [automate quota adjustments](https://docs.cloud.google.com/docs/quotas/quota-adjuster.md.txt)

In most cases, when you attempt to consume more of a resource than its quota
allows, the system blocks access to the resource, and the task that
you're trying to perform fails.

Quotas generally apply at the Google Cloud project
level. Your use of a resource in one project doesn't affect
your available quota in another project. Within a Google Cloud project, quotas
are shared across all applications and IP addresses.


For more information, see the
[Cloud Quotas overview](https://docs.cloud.google.com/docs/quotas/overview.md.txt).

| Quota | Value |
|---|---|
| Total number of data stores per project | 100^1^ |
| Total number of engines per project | 150^2^ |
| Regional number of data stores per project per location (Global, US, EU) | 100 |
| Regional number of documents per project per location (Global, US, EU) | 10,000,000 |
| Regional number of engines per project per location (Global, US, EU) | 150 |


^1^ Due to a technical limitation, the maximum quota for data stores is
500 per project. If you need more data stores, use new projects.

Each entity in a data store is counted as a data store instance and,
therefore, counts toward this quota. For example, a data store with three
entities counts as three data stores against your quota.


^2^ Due to a technical limitation, the maximum quota for engines is 500
per project. If you need more engines, use new projects.

> [!NOTE]
> **Note:** The number of data stores, documents, and engines across all locations can't exceed the total per-project quota for that resource. For example, if you already have 60 data stores in the `eu` multi-region and 40 in the `us` multi-region, you can't create another data store because the overall data store quota for the project is 100.

### Rate quotas

The following rate quotas apply to Discovery Engine API requests.


There are also *system limits* on Gemini Enterprise resources.
System limits can't be changed.

| Quota | Value |
|---|---|
| Complete query requests per minute per project | 300 |
| Regional search requests per minute per project per location (Global, US, EU) | 300 |

## Pay-as-you-go usage above quota

Feature usage is restricted when you exceed the feature quotas of your
Gemini Enterprise edition. To avoid interruptions, a Gemini Enterprise
administrator can turn on the **Pay-as-you-go usage above quota** setting.
Pay-as-you-go usage above quota (formerly referred to as overages) is available
only if your project has at least one active, non-free-trial subscription. If
your project is linked to a self-serve Cloud Billing account, you pay for
usage above quota with
[prepaid credits](https://docs.cloud.google.com/gemini/enterprise/docs/manage-prepaid-credits.md.txt). If it's
linked to an
[invoiced Cloud Billing account](https://docs.cloud.google.com/billing/docs/concepts.md.txt#billing_account_types)
or to a [billing subaccount](https://docs.cloud.google.com/billing/docs/concepts.md.txt#subaccounts) of an invoiced
billing account, usage above quota is billed on your monthly invoice. Free-trial subscriptions
include the base pooled quotas for their edition and aren't eligible for
pay-as-you-go usage. AI developer tools are included in free-trial
subscriptions, with a limited quota, only if your project is linked to an
invoiced billing account. To verify your account
type, see
[Find out your Cloud Billing account type and charging cycle](https://docs.cloud.google.com/billing/docs/how-to/billing-cycle.md.txt#view-your-charging-cycle).

> [!NOTE]
> **Note:** Claude models are available only with pay-as-you-go usage. Ensure that you have turned on **Pay-as-you-go usage above quota** for all editions where you turn on Claude models for your end users.

Pay-as-you-go charges apply as defined in the following table for all
license-based editions (Standard, Plus, Frontline, EDU, and Emerging Market
editions).

If you have a pay-as-you-go subscription, you pay for usage at the
pay-as-you-go rates listed in the following table.

> [!NOTE]
> **Note:** Usage that exceeds the quota for **storage + data indexing** automatically incurs pay-as-you-go charges. Because storage and data indexing quota is pooled per project and location across all editions, any usage exceeding the single shared pool for the project and location incurs pay-as-you-go charges. You pay storage and data indexing charges prorated by the duration you store the data. For example, if you store 30 GiB of excess data for one day in a 30-day month, you pay $5 (30 GiB / 30 days × $5 per GiB per month).

### Pay-as-you-go charges for features above quota

Prices are listed in US Dollars (USD). If you pay in a currency other than USD,
the prices listed in your currency on
[Cloud Platform SKUs](https://cloud.google.com/skus/) apply. Charges are
subject to a variable support fee depending on the support service. For more
information on the support services, see
[Compare support services](https://docs.cloud.google.com/support/docs/overview.md.txt#compare-support).

|   || Gemini Enterprise Quota units | Gemini Enterprise Pay-as-you-go charges above quota |
| Quotas (Pooled or Unpooled) || Pooled across users within the edition per project and location | Pooled across users within the edition per project and location |
| Foundational engagement layer | Storage + data indexing | GiB | $5 per GiB per month |
| Foundational engagement layer |
| Foundational engagement layer |
| Foundational engagement layer |
| Foundational engagement layer |
| Foundational engagement layer |
| Foundational engagement layer |
|---|---|---|---|
| Assistant - Gemini models | Queries per day | [Agent Platform prices](https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#cost-of-building-and-deploying-ai-models-in-agent-platform) |
| Assistant - Claude models | n/a - only available through Pay-as-you-go above quota charges. | [Claude pricing](https://docs.cloud.google.com/gemini/enterprise/docs/quotas-and-pay-as-you-go-usage.md.txt#claude-pricing) |
| No-code agent building tools - create | Agents per day | n/a |
| No-code agent building tools - use | Based on underlying agent actions | [Agent Platform prices](https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#cost-of-building-and-deploying-ai-models-in-agent-platform) |
| Video generation | Video generation requests per day | [Agent Platform prices](https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#cost-of-building-and-deploying-ai-models-in-agent-platform) |
| Image generation | Images per day | [Agent Platform prices](https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#cost-of-building-and-deploying-ai-models-in-agent-platform) |
| Gemini Notebook for business - create \& publish | Gemini Notebook for business limits^1^ | n/a |
| Deep Research | Queries per day | [Agent Platform prices](https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#cost-of-building-and-deploying-ai-models-in-agent-platform) |
| Claude models | n/a - only available through Pay-as-you-go above quota charges. | [Claude pricing](https://docs.cloud.google.com/gemini/enterprise/docs/quotas-and-pay-as-you-go-usage.md.txt#claude-pricing) |

^1^ For information about Gemini Notebook for business usage limits, see the [Gemini Notebook for business documentation](https://docs.cloud.google.com/gemini/enterprise/notebooklm-enterprise/docs/overview.md.txt#usage-limits).

^2^ AI developer tools are
available with upgraded self-serve (online) and invoiced
[Cloud Billing accounts](https://docs.cloud.google.com/billing/docs/concepts.md.txt#billing_account_types), or
with a [billing subaccount](https://docs.cloud.google.com/billing/docs/concepts.md.txt#subaccounts) of an invoiced
billing account. Free-trial subscriptions include AI developer tools, with a
limited quota, only if your project is linked to an invoiced billing account.
For more information, see
[Do free-trial licenses include the AI developer tools quota?](https://docs.cloud.google.com/gemini/enterprise/docs/licenses-faqs.md.txt#free-trial-ai-developer-tools-quota)
^3^ Although quotas are listed as a monthly per-user amount, Gemini Enterprise enforces them on a rolling seven-day basis as a shared pool. Gemini Enterprise calculates your project's weekly quota by dividing the monthly per-user value by four and multiplying it by your project's total licensed seats, including free-trial seats. Any user in your edition can draw from this shared weekly pool. Unused quota doesn't roll over to the next week.

### Claude pricing

Claude models are available on the Gemini Enterprise app only with
pay-as-you-go usage. Ensure that you have turned on
**Pay-as-you-go usage above quota** for all editions where you want to enable
Claude models.

Pay-as-you-go charges for Claude models apply as defined in the following table:

> [!NOTE]
> **Note:** Claude model pricing and discounts in the Gemini Enterprise app are distinct from pricing procured through Google Cloud Marketplace.

### Global

| Model | Type | Model price (/1M tokens) =\< 200K input tokens | Model price (/1M tokens) \> 200K input tokens |
| Claude Opus 5.5 | Input | $4.00 | $4.00 |
| Claude Opus 5.5 |
| Claude Opus 5.5 |
| Claude Opus 5.5 |
| Claude Opus 5.5 |
|---|---|---|---|
| Output | $20.00 | $20.00 |
| 5m Cache Write | $5.00 | $5.00 |
| 1h Cache Write | $8.00 | $8.00 |
| Cache Hit | $0.20 | $0.20 |
| Output | $10.00 | $10.00 |
| 5m Cache Write | $2.50 | $2.50 |
| 1h Cache Write | $4.00 | $4.00 |
| Cache Hit | $0.20 | $0.20 |

### US Multi-Region (US)

| Model | Type | Model price (/1M tokens) =\< 200K input tokens | Model price (/1M tokens) \> 200K input tokens |
| Claude Opus 5.5 | Input | $4.40 | $4.40 |
| Claude Opus 5.5 |
| Claude Opus 5.5 |
| Claude Opus 5.5 |
| Claude Opus 5.5 |
|---|---|---|---|
| Output | $22.00 | $22.00 |
| 5m Cache Write | $5.50 | $5.50 |
| 1h Cache Write | $8.80 | $8.80 |
| Cache Hit | $0.22 | $0.22 |
| Output | $11.00 | $11.00 |
| 5m Cache Write | $2.75 | $2.75 |
| 1h Cache Write | $4.40 | $4.40 |
| Cache Hit | $0.22 | $0.22 |

### EU Multi-Region (EU)

| Model | Type | Model price (/1M tokens) =\< 200K input tokens | Model price (/1M tokens) \> 200K input tokens |
| Claude Opus 5.5 | Input | $4.40 | $4.40 |
| Claude Opus 5.5 |
| Claude Opus 5.5 |
| Claude Opus 5.5 |
| Claude Opus 5.5 |
|---|---|---|---|
| Output | $22.00 | $22.00 |
| 5m Cache Write | $5.50 | $5.50 |
| 1h Cache Write | $8.80 | $8.80 |
| Cache Hit | $0.22 | $0.22 |
| Output | $11.00 | $11.00 |
| 5m Cache Write | $2.75 | $2.75 |
| 1h Cache Write | $4.40 | $4.40 |
| Cache Hit | $0.22 | $0.22 |