Vertex AI supports a curated list of models developed by Google partners. Partner models can be used with Vertex AI as a model as a service (MaaS) and are offered as a managed API. When you use a partner model, you continue to send your requests to Vertex AI endpoints. Partner models are serverless so there's no need to provision or manage infrastructure.
Partner models can be discovered using Model Garden. You can also deploy models using Model Garden. For more information, see Explore AI models in Model Garden. While information about each available partner model can be found on its model card in Model Garden, only third-party models that perform as a MaaS with Vertex AI are documented in this guide.
Anthropic Claude models are an example of third-party managed models that are available to use on Vertex AI. To learn how to use Claude models, see Use the Claude models from Anthropic.
Predictable performance with capacity assurance
Google offers provisioned throughput for partner models that reserves throughput capacity for your models for a fixed fee. You decide on the throughput capacity and in which regions to reserve that capacity. Because provisioned throughput requests are prioritized over the standard pay-as-you-go requests, provisioned throughput provides increased availability. When the system is overloaded, your requests can still be completed as long as the throughput remains under your reserved throughput capacity. For more information or to subscribe to the service, Contact sales.