Starting April 29, 2025, Gemini 1.5 Pro and Gemini 1.5 Flash models are not available in projects that have no prior usage of these models, including new projects. For details, see Model versions and lifecycle.
Stay organized with collections
Save and categorize content based on your preferences.
Single Zone Provisioned Throughput lets you reserve
throughput in specific regions where only one zone is
available. This option provides
predictable performance for Gemini models in use cases where ML
processing is required.
To view the list of supported models and regions, see
Deployments and endpoints. For the list of
regions and models that support ML processing, see
ML processing.
Features of Single Zone Provisioned Throughput
This section outlines the key features of Single Zone Provisioned Throughput:
Pricing and units are consistent with standard Provisioned Throughput:
Single Zone Provisioned Throughput uses the same measure of throughput (GSUs),
pricing, and terms as
standard Provisioned Throughput.
Single Zone Provisioned Throughput supports in-region ML processing: All requests are processed in the
purchased region, including traffic that exceeds your purchased amount of
throughput. This traffic is billed at the
pay-as-you-go rate
using buffer capacity in the region.
You control the overages: You can
control overflow traffic
using the same headers as with standard Provisioned Throughput.
You can monitor your order: You can monitor your Single Zone Provisioned Throughput order using the existing
Provisioned Throughput monitoring capabilities.
Limitations
Single Zone Provisioned Throughput has the following limitations:
Single Zone Provisioned Throughput does not integrate with or support
Batch requests
or Fine Tuning.
In regions without ML processing, latency for Single Zone Provisioned Throughput might be higher than
standard Provisioned Throughput or pay-as-you-go.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-27 UTC."],[],[],null,["# Single Zone Provisioned Throughput lets you reserve\nthroughput in specific regions where only one [zone](/docs/geography-and-regions) is\navailable. This option provides\npredictable performance for Gemini models in use cases where ML\nprocessing is required.\n\nTo view the list of supported models and regions, see\n[Deployments and endpoints](/vertex-ai/generative-ai/docs/learn/locations). For the list of\nregions and models that support ML processing, see\n[ML processing](/vertex-ai/generative-ai/docs/learn/locations#canada).\n\nFeatures of Single Zone Provisioned Throughput\n----------------------------------------------\n\nThis section outlines the key features of Single Zone Provisioned Throughput:\n\n- **Pricing and units are consistent with standard Provisioned Throughput** :\n Single Zone Provisioned Throughput uses the same measure of throughput ([GSUs](/vertex-ai/generative-ai/docs/provisioned-throughput/measure-provisioned-throughput#gsu-burndown-rate)),\n [pricing](/vertex-ai/generative-ai/pricing#provisioned-throughput), and terms as\n standard [Provisioned Throughput](/vertex-ai/generative-ai/docs/provisioned-throughput/purchase-provisioned-throughput).\n\n- **Single Zone Provisioned Throughput supports in-region ML processing** : All requests are processed in the\n purchased region, including traffic that exceeds your purchased amount of\n throughput. This traffic is billed at the\n [pay-as-you-go rate](/vertex-ai/generative-ai/pricing#provisioned-throughput)\n using buffer capacity in the region.\n\n- **You control the overages** : You can\n [control overflow traffic](/vertex-ai/generative-ai/docs/provisioned-throughput/use-provisioned-throughput#use-rest-api)\n using the same headers as with standard Provisioned Throughput.\n\n- **You can monitor your order** : You can monitor your Single Zone Provisioned Throughput order using the existing\n [Provisioned Throughput monitoring](/vertex-ai/generative-ai/docs/provisioned-throughput/use-provisioned-throughput#monitor_provisioned_throughput) capabilities.\n\nLimitations\n-----------\n\nSingle Zone Provisioned Throughput has the following limitations:\n\n- Single Zone Provisioned Throughput is not a Covered Service and is excluded from the\n [Gemini Online Inference on Vertex AI Service Level Agreement](/vertex-ai/generative-ai/sla).\n\n- Single Zone Provisioned Throughput does not integrate with or support\n [Batch requests](/vertex-ai/generative-ai/docs/multimodal/batch-prediction-gemini#batch_prediction_use_case)\n or [Fine Tuning](/vertex-ai/generative-ai/docs/models/tune-models).\n\n- In regions without ML processing, latency for Single Zone Provisioned Throughput might be higher than\n standard Provisioned Throughput or pay-as-you-go.\n\nPurchase Single Zone Provisioned Throughput\n-------------------------------------------\n\nFor assistance with purchasing Single Zone Provisioned Throughput, [contact your Google Cloud account representative](/contact).\n\nWhat's next\n-----------\n\n- [Purchase standard Provisioned Throughput.](/vertex-ai/generative-ai/docs/purchase-provisioned-throughput)"]]