Azure Document Intelligence vs OpenDocRouter

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.

OpenDocRouter

One endpoint reaches 11 parsing models, each with a dated recipe version, a published token price and a ParseBench score, and failed pages aren't charged. The service launched on 7 October 2026, so it has no status page, incident history, SLA or changelog yet, and no key scopes were found in the reviewed documentation.

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

OpenDocRouter

1. Call GET /v1/models first, which needs no key, and choose a model by avg_charge_per_page_usd and its ParseBench scores. Send its id as model
2. Send cache: true on any request you might repeat. Without it the markdown exists only in the POST response and a resend is charged as a new request
3. Raise the SDK timeout above its 60-second default for sync parses. Pages can run for 270 seconds and the SDKs retry a timed-out request twice
4. Check every page's status before using its markdown. A 200 can be partial, and failed pages can be resent alone with pages
5. Treat 402 as final until credit is added. The hold is the model's maximum charge per page times the page count, and GET /v1/credits shows available_usd