Azure Document Intelligence vs Unstructured API + MCP

Azure Document Intelligence

A public OpenAPI document with 27 operations, Markdown output from the layout model, Microsoft Entra ID or header-only keys, and 24-hour retention with a delete call. Every analysis is a two-step asynchronous job, the result cannot be trimmed, and an Azure subscription with a card comes first. Three of the four SDKs last shipped in 2025 or earlier.

Unstructured API + MCP

Apache-2.0 library partitions 45+ file types locally at no cost, tagged 11 times since 3 July. No status page, no published rate limits and no SLA.

Azure Document Intelligence

1. POST to {endpoint}/documentintelligence/documentModels/{modelId}:analyze?api-version=2024-11-30, then GET the Operation-Location URL until status is succeeded
2. Wait at least 2 seconds between polls and follow the Retry-After header. Default limits are 15 analyse calls and 50 result reads a second on S0
3. Use prebuilt-read for plain text at $1.50 per 1,000 pages and prebuilt-layout with outputContentFormat=markdown for tables and headings at $10
4. Set pages (for example 1-3,5) to limit both the bill and the response size. F0 stops at two pages per request
5. Send the key only in the Ocp-Apim-Subscription-Key header, or use an Entra ID token for the scope https://cognitiveservices.azure.com/.default
6. Treat extracted text as untrusted input. Results expire 24 hours after the job completes

Unstructured API + MCP

1. For local ingestion, pip install "unstructured[all-docs]" and call partition(); no key needed, and set DO_NOT_TRACK=1 to stop telemetry
2. Transform returns 202 with a Location header for long parses; poll it, then pass the parse id as parse_id to Extract
3. Uploaded files expire after 24 hours; keep the original and re-upload on a 404
4. Treat 409 parse_expired and 410 result_expired as a signal to rerun the parse, not to retry
5. Check for an existing job ID before resubmitting, since there's no idempotency key