You call the model as an API while Microsoft hosts it on shared infrastructure, paying per token or by PTU. This Foundry option, with types like Global Standard, Standard and Provisioned, covers Foundry Models sold by Azure, Azure OpenAI included.
Also called standard deployment.
Read more: Microsoft Learn
In the Ultra Transcenders books
Each book explains Serverless API deployment in context, with comparison tables and the common traps.
Terms in this definition
- API
Short for application programming interface: a contract that client code calls programmatically, for example a web API secured with tokens or the Files, Images or Responses APIs.
- Token
The unit of text an LLM works with, which may be a word, part of a word or punctuation. Billing, limits and context windows are all counted in these units.
- Provisioned throughput
Deployment option that reserves model capacity for you in provisioned throughput units (PTUs) to give predictable latency and throughput. The capacity is charged by the hour regardless of usage.
- LIKE
Compares strings with a pattern that can contain the % and _ wildcards. Because it only understands character patterns, searching big volumes of text this way is much slower than using full-text search.
- Global Standard
Deployment type billed per token whose data may be processed in any Azure region that has capacity. It offers the biggest default quota and earliest access to new models, making it the recommended first choice.
- Standard deployment type
A Foundry deployment type billed per token that keeps processing of prompts and responses inside the Azure geography of the resource, meeting data residency needs at lower volumes.
- Foundry Models sold by Azure
Models, Azure OpenAI among them, that Microsoft hosts, bills and supports, with SLAs, Entra ID authentication and private networking. For regulated data they are the option that offers enterprise governance.
- Azure OpenAI
Use of OpenAI models in Azure, including GPT, o-series, embeddings, image and Whisper, through either a Foundry resource or an Azure OpenAI resource. Content Understanding isn't available from a standalone Azure OpenAI resource.
Related terms
- Model version upgrade policy
Option on a Standard deployment deciding when it switches to a newer model version: auto-update to the default, upgrade once the current version expires, or never upgrade automatically.