配額會指定您可使用的可計數共用資源數量。配額是由 Google Cloud 服務定義,例如 Gemini for Google Cloud。
系統限制是無法變更的固定值。
Google Cloud 會使用配額來確保公平性,並減少資源使用量和可用性暴增的情況。配額會限制專案可使用的Google Cloud 資源 Google Cloud 數量。配額適用於各種資源類型,包括硬體、軟體和網路元件。舉例來說,配額可以限制對服務發出的 API 呼叫數、專案並行使用的負載平衡器數量,或是可建立的專案數量。配額可以預防服務過載,進而保障Google Cloud 使用者社群的權益。配額也能協助您管理自己的 Google Cloud 資源。
[[["容易理解","easyToUnderstand","thumb-up"],["確實解決了我的問題","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["難以理解","hardToUnderstand","thumb-down"],["資訊或程式碼範例有誤","incorrectInformationOrSampleCode","thumb-down"],["缺少我需要的資訊/範例","missingTheInformationSamplesINeed","thumb-down"],["翻譯問題","translationIssue","thumb-down"],["其他","otherDown","thumb-down"]],["上次更新時間:2025-09-04 (世界標準時間)。"],[[["\u003cp\u003eGemini for Google Cloud has quotas and system limits that define the usage of shared resources, with quotas being adjustable and system limits being fixed.\u003c/p\u003e\n"],["\u003cp\u003eQuotas are applied at the project level and restrict the usage of resources, such as API calls, to ensure fairness and prevent service overload.\u003c/p\u003e\n"],["\u003cp\u003eGemini for Google Cloud enforces daily and per-second quotas on requests, such as code completion and generation, which vary depending on the request type and if Gemini Code Assist is being used, or if using Gemini in BigQuery.\u003c/p\u003e\n"],["\u003cp\u003eFor users of Gemini in BigQuery with BigQuery Enterprise Plus edition, quotas are based on the daily average use of Enterprise Plus slot-hours in the previous month, and default quotas apply initially and mid-month.\u003c/p\u003e\n"],["\u003cp\u003eQuotas can be managed and increased through the Google Cloud console, allowing users to adjust their resource allocation as needed.\u003c/p\u003e\n"]]],[],null,["# Quotas and limits\n\nThis document lists the quotas and system limits that apply to\nGemini for Google Cloud.\n\n- *Quotas* specify the amount of a countable, shared resource that you can use. Quotas are defined by Google Cloud services such as Gemini for Google Cloud.\n- *System limits* are fixed values that cannot be changed.\n\n\u003cbr /\u003e\n\nGoogle Cloud uses quotas to help ensure fairness and reduce\nspikes in resource use and availability. A quota restricts how much of a\nGoogle Cloud resource your Google Cloud project can use. Quotas\napply to a range of resource types, including hardware, software, and network\ncomponents. For example, quotas can restrict the number of API calls to a\nservice, the number of load balancers used concurrently by your project, or the\nnumber of projects that you can create. Quotas protect the community of\nGoogle Cloud users by preventing the overloading of services. Quotas also\nhelp you to manage your own Google Cloud resources.\n\nThe Cloud Quotas system does the following:\n\n- Monitors your consumption of Google Cloud products and services\n- Restricts your consumption of those resources\n- Provides a way to [request changes to the quota value](/docs/quotas/help/request_increase) and [automate quota adjustments](/docs/quotas/quota-adjuster)\n\nIn most cases, when you attempt to consume more of a resource than its quota\nallows, the system blocks access to the resource, and the task that\nyou're trying to perform fails.\n\nQuotas generally apply at the Google Cloud project\nlevel. Your use of a resource in one project doesn't affect\nyour available quota in another project. Within a Google Cloud project, quotas\nare shared across all applications and IP addresses.\n\n\nThere are also *system limits* on Gemini resources.\nSystem limits can't be changed.\n\nRequests per second\n-------------------\n\nGemini for Google Cloud enforces quotas on requests per second\nfor each user in a project.\n\nRequests per day\n----------------\n\nGemini for Google Cloud enforces quotas for the total number of\nrequests per day for each user in a project.\n\nQuotas for Gemini Code Assist\n-----------------------------\n\nGemini Code Assist enforces quotas for certain features.\n\nQuotas for agent mode and the Gemini CLI\n----------------------------------------\n\nQuotas for requests from Gemini Code Assist agent mode and the\nGemini CLI are combined. When in agent mode or when using the\nGemini CLI, one prompt might result in multiple requests.\n\nQuotas for Gemini in BigQuery\n-----------------------------\n\nFor code assistance features, the quota for Gemini Code Assist\nand Gemini in BigQuery code requests for features\nlike code completion and code generation is the same.\n\nFor customers using Gemini in BigQuery with\nBigQuery on-demand compute or with Enterprise or Enterprise Plus editions,\nthe quotas for advanced features such as data insights are provided based upon\nthe daily average use of TiB scanned or the slot-hours for the last full\ncalendar month. This quota applies to the organization level and is available to\nall projects in that organization. Quotas are rounded up to the nearest 100\nslot-hour usage.\n\n**Example**: An organization that has an Enterprise edition reservation\nwith 100 slots as its baseline will use an average of 2,400 slot-hours each\nday (100 slots \\* 24 hours = 2,400 slot-hours). As a result, in the following\nmonth they get the following daily quotas:\n\n- 120 chat, visualizations, data insights table scans and automated metadata generations per day\n\nIf your organization has not purchased any BigQuery Enterprise edition, Enterprise\nPlus edition slots, or on-demand compute (TiB) until now, then after your first usage you will receive the default quota of the following for the first full calendar month:\n\n- 250 chat, visualizations, data insights table scans, and automated metadata generations per day\n\nIf you start using on-demand compute, Enterprise edition or Enterprise Plus edition reservations mid-month, then the\ndefault quota applies until the end of the following month.\n\nRequest a quota increase\n------------------------\n\nTo adjust most quotas, use the Google Cloud console.\nFor more information, see\n[Request a quota adjustment](/docs/quotas/help/request_increase).\n\n\u003cbr /\u003e"]]