Azure OpenAI Service is Microsoft's cloud service that runs OpenAI's language, reasoning and multimodal models on Microsoft Azure. Microsoft now presents it as Azure OpenAI in Foundry Models, part of its Microsoft Foundry platform. A language model is a neural network that reads text and writes new text, such as an answer, a summary or an email.
A developer deploys a chosen model, sends requests to its API and receives generated text, audio or images back. Around the models, the service adds Azure features: data privacy controls, a choice of regional, data-zone or global processing, tools that filter harmful content, fine-tuning of a model on a company's own data, and connections to other Azure services such as Cosmos DB and Azure AI Search.
Use is billed per million tokens (a token is a piece of a word) with pay-per-use pricing, or as reserved capacity in Provisioned Throughput Units (PTUs). The Batch API returns results within 24 hours at half the Global Standard price.