Document Understanding was released with an asynchronous API, which is useful for analysis of batches and large document files. However, it requires staging documents in object storage and also obtaining results from object storage. For low latency use cases like search and when working with sensitive data like protected health information (PHI), having a synchronous API not dependent on object storage is desirable. Such a synchronous API is now generally available.

AnalyzeDocument represents the synchronous API. AnalyzeDocument supports both inline source documents encoded as a Base64 string and also documents located in object storage.