[[["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)。"],[],[],null,["# Throughput quota\n\nVertex AI offers two ways to manage throughput for your generative AI models, which lets you balance cost, flexibility, and performance. You can either use a flexible pay-as-you-go model or reserve a dedicated amount of throughput for a fixed price.\n\n\u003cbr /\u003e\n\nPay-as-you-go\n-------------\n\nFor the default pay-as-you-go model, Vertex AI uses\n[Dynamic Shared Quota](/vertex-ai/generative-ai/docs/dynamic-shared-quota),\nwhich doesn't have a predefined usage limit. Instead, you get access to a large,\nshared pool of resources that are dynamically allocated based on real-time\navailability and demand.\n\nThis model allows your workloads to use more resources when they are available.\nIf you receive a `resource exhausted` (429) error, it means the shared pool is\ntemporarily experiencing high demand from many users at once. You should\nimplement retry mechanisms in your application, as availability can change\nquickly.\n\nReserved Capacity\n-----------------\n\nFor critical production applications that require consistent performance and\npredictable costs, you can use\n[Provisioned Throughput](/vertex-ai/generative-ai/docs/provisioned-throughput/overview).\nProvisioned Throughput is a fixed-cost subscription that reserves a\nspecific amount of throughput for your models in a chosen location.\n\nWhat's next\n-----------\n\n- Learn more about [Dynamic Shared Quota](/vertex-ai/generative-ai/docs/dynamic-shared-quota).\n- Learn more about [Provisioned Throughput](/vertex-ai/generative-ai/docs/provisioned-throughput/overview).\n- Learn more about [Google Cloud quotas](/docs/quotas/overview)."]]