Azure AI Document Intelligence
Microsoft AzureManaged document-processing service on Azure, formerly Form Recognizer, that converts documents into markdown or structured JSON with layout, tables, selection marks and key-value pairs, and supports custom models trained on a customer's own forms.
Formerly named Form Recognizer; the product page carries the current name.
Openness
1 high confidence- license
- Proprietary
- service
- proprietary(Microsoft Azure managed service)
- source
- closed(no implementation is published)
It is a commercial managed service with no published implementation, and it cannot be self-hosted. There is no source at all to weigh here.
- https://azure.microsoft.com/products/ai-services/ai-document-intelligence recorded 2026-09-16
Microsoft's Azure AI Document Intelligence product page, describing extraction of text, tables, structure and key-value pairs from documents with prebuilt and custom models. Establishes a managed Azure service with no published implementation.
Adoption
not assessedNo usage figure is published for this service specifically, and it publishes no countable artifact - no package, repository or registry entry - so no level is assigned rather than one being inferred from the vendor's platform as a whole.
- https://azure.microsoft.com/products/ai-services/ai-document-intelligence recorded 2026-09-16
The product page, read for a usage disclosure; it publishes none specific to this service.
Capability
5 medium confidenceAzure AI Document Intelligence's prebuilt and custom models turn documents into typed structure rather than plain text, and its markdown output can be fed directly into a model as context. Its capability matches Google Document AI's, its direct counterpart.
- https://azure.microsoft.com/products/ai-services/ai-document-intelligence recorded 2026-09-16
Microsoft's Azure AI Document Intelligence product page, describing extraction of text, tables, structure and key-value pairs from documents with prebuilt and custom models. Establishes a managed Azure service with no published implementation.
Verified 2026-09-16