Azure OpenAI provisioned throughput reservation allocates throughput with predictable costs, with monthly and annual reservations available to reduce overall spend. This is a Global Provisioned reservation eligible for use across multiple Azure regions for generative AI workloads.
Specification
Reservations are purchased per deployment type (Global, Data Zone, or Regional) and can be scoped to cover one or more subscriptions or resource groups.
In exchange for a 1-month or 1-year commitment, you receive a discounted effective $/PTU/hr rate.
Model-independent pricing pool shared across supported Azure OpenAI and Foundry models.
Billed per Provisioned Throughput Unit (PTU) deployed.
No capacity guarantee with reservation purchase.
Global scope allows deployment flexibility across Azure regions.
