Azure AI Document Intelligence

Best for: Prototypes and side projects - free to start, no sales call; Regulated or enterprise workloads - compliance attestations and an enterprise plan; AI agents and automation - an agent-ready surface (MCP / llms.txt)

• ████▒░░░░░
  45 / 100
  Agent friendliness
• ██████████
  100 / 100
  Pricing transparency
• ████████▒░
  85 / 100
  Setup speed
• ██▒░░░░░░░
  25 / 100
  Docs quality
• ██████████
  100 / 100
  Procurement ease
• █████████░
  90 / 100
  Trust readiness

Scores are computed deterministically from this profile's published, sourced fields (pricing, compliance, capabilities, docs and developer-surface signals) - not from reviews or paid placement. Each axis is 0-100; an unknown signal scores 0 for that axis. Procurement ease is the inverse of buying friction (higher = easier to adopt).

Pricing model

Usage-based [2]learn.microsoft.com/en-us/azure/ai-services/document-intelligence/service-limits“Document Intelligence billing is calculated monthly based on the model type and the number of pages analyzed.”azure.microsoft.com/en-us/pricing/details/document-intelligence/

Published pricing

✓ Yes [3]learn.microsoft.com/en-us/azure/ai-services/document-intelligence/service-limits“For **Free (F0)** pricing tier see also monthly allowances at the pricing page (https://azure.microsoft.com/pricing/details/ai-document-intelligence/).”azure.microsoft.com/en-us/pricing/details/document-intelligence/

Free tier

✓ Yes [4]learn.microsoft.com/en-us/azure/ai-services/document-intelligence/service-limits“Document Intelligence offers a free tier (F0) where you can test all the Document Intelligence features. The free tier limits analyze response to only the first two pages in a request.”azure.microsoft.com/en-us/pricing/details/document-intelligence/learn.microsoft.com/en-us/azure/ai-services/document-intelligence/faq“For free-tier (F0) resources, **only the first two pages** are analyzed whether you're using Document Intelligence Studio, the REST API, or client libraries.”

Free tier details

Document Intelligence offers a persistent free tier (F0) for testing all features. F0 includes 500 pages/month; no time limit. F0 limits document analysis to only the first two pages per request, max document size 4 MB, and 1 TPS. No SLA is provided on the free tier.

Self-serve signup

✓ Yes [5]learn.microsoft.com/en-us/azure/ai-services/document-intelligence/faq“You need an active Azure account (https://azure.microsoft.com/pricing/purchase-options/azure-account) and subscription with at least a Reader role to access Document Intelligence Studio.”

Requires sales call

✗ No

Enterprise plan

✓ Yes [6]learn.microsoft.com/en-us/azure/ai-services/document-intelligence/service-limits“Document Intelligence has a commitment-based pricing model for large workloads.”azure.microsoft.com/en-us/pricing/details/document-intelligence/

• Receipts / invoices
• ID documents
• Bank statements
• Table extraction
• Custom models
• LLM / RAG-ready output

Supported actions

analyze_document (prebuilt-read), analyze_document (prebuilt-layout), analyze_document (prebuilt-invoice), analyze_document (prebuilt-receipt), analyze_document (prebuilt-idDocument), analyze_document (prebuilt-contract), analyze_document (prebuilt-creditCard), analyze_document (prebuilt-check.us), analyze_document (prebuilt-payStub.us), analyze_document (prebuilt-bankStatement), analyze_document (prebuilt-healthInsuranceCard.us), analyze_document (prebuilt-marriageCertificate.us), analyze_document (prebuilt-mortgage.us.1003), analyze_document (prebuilt-mortgage.us.1004), analyze_document (prebuilt-mortgage.us.1005), analyze_document (prebuilt-mortgage.us.1008), analyze_document (prebuilt-mortgage.us.closingDisclosure), analyze_document (prebuilt-tax.us), analyze_document (prebuilt-tax.us.w2), analyze_document (prebuilt-tax.us.1040), analyze_document (prebuilt-tax.us.1098), analyze_document (prebuilt-tax.us.1099), build_custom_model (template), build_custom_model (neural), build_custom_classifier, compose_models, copy_model, delete_analyze_result, get_analyze_result, list_models, get_model, delete_model, ocr_high_resolution (add-on), formula_extraction (add-on), font_property_extraction (add-on), barcode_extraction (add-on), searchable_pdf_generation (add-on), query_fields (add-on), key_value_pairs (add-on) [7]learn.microsoft.com/en-us/azure/ai-services/document-intelligence/overview“Document Intelligence supports optional features that you can enable or disable depending on the document extraction scenario: ocr.highResolution ... ocr.formula ... ocr.font ... ocr.barcode ... Searchable PDF ... queryFields ... keyValuePairs”learn.microsoft.com/en-us/azure/ai-services/document-intelligence/overview“prebuilt-read ... prebuilt-layout ... prebuilt-invoice ... prebuilt-receipt ... prebuilt-idDocument ... prebuilt-contract ... prebuilt-creditCard ... prebuilt-check ... prebuilt-payStub.us ... prebuilt-bankStatement ... prebuilt-healthInsuranceCard.us ... prebuilt-marriageCertificate.us ... prebuilt-mortgage.us.1003 ... prebuilt-tax.us.w2 ... prebuilt-tax.us.1040 ... prebuilt-tax.us.1098 ... prebuilt-tax.us.1099”learn.microsoft.com/en-us/rest/api/aiservices/document-models/analyze-document“POST {endpoint}/documentintelligence/documentModels/{modelId}:analyze?_overload=analyzeDocument&api-version=2024-11-30”

Regions

East US, East US 2, West US, West US 2, West US 3, Central US, North Central US, South Central US, Canada Central, Canada East, North Europe, West Europe, UK South, France Central, Germany West Central, Switzerland North, East Asia, Southeast Asia, Australia East, Japan East, Korea Central, Brazil South, South Africa North, UAE North, Azure Government (US), Azure China (21Vianet), Azure US Government (Fairfax) [8]learn.microsoft.com/en-us/azure/ai-services/document-intelligence/overview“Azure Document Intelligence in Foundry Tools is a cloud-based Foundry Tools service that you can use to build intelligent document processing solutions. ... For information on region access, see Product availability by region.”learn.microsoft.com/en-us/azure/ai-services/document-intelligence/faq“Document Intelligence Studio has separate URL endpoints for sovereign cloud regions: URL for the Azure US Government cloud (Azure Fairfax) ... URL Microsoft Azure operated by 21Vianet (Azure China)”

Languages

Abaza, Abkhazian, Achinese, Acoli, Adangme, Adyghe, Afar, Afrikaans, Akan, Albanian, Algonquin, Arabic, Asturian, Azerbaijani, Bambara, Bashkir, Basque, Belarusian, Bislama, Bosnian, Breton, Bulgarian, Catalan, Cebuano, Chamorro, Chinese Simplified, Chinese Traditional, Cornish, Corsican, Croatian, Czech, Danish, Dari, Dutch, English, Estonian, Faroese, Fijian, Filipino, Finnish, French, Galician, German, Greek, Gujarati (detection only), Haitian Creole, Hawaiian, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Interlingua, Irish, Italian, Japanese, Javanese, Kazakh, Korean, Kurdish, Latin, Latvian, Lithuanian, Luxembourgish, Macedonian, Malay, Maltese, Maori, Marathi, Mongolian, Nepali, Norwegian, Occitan, Persian, Polish, Portuguese, Punjabi, Romanian, Romansh, Russian, Samoan, Sanskrit, Scottish Gaelic, Serbian, Slovak, Slovenian, Somali, Spanish, Swahili, Swedish, Tajik, Tamil, Tatar, Thai, Turkish, Turkmen, Ukrainian, Urdu, Uzbek, Vietnamese, Welsh, Zulu [9]learn.microsoft.com/en-us/azure/ai-services/document-intelligence/language-support-ocr“Azure Document Intelligence in Foundry Tools models provide multilingual document processing support. Our language support capabilities enable your users to communicate with your applications in natural ways and empower global outreach.”learn.microsoft.com/en-us/azure/ai-services/document-intelligence/language-support-ocr“The following table lists read model language support for extracting and analyzing printed text. | Language | Code (optional) | | --- | --- | | Abaza | `abq` | | Abkhazian | `ab` | | Achinese | `ace` | ... | Zulu | `zu` |”

Input types

PDF, JPEG, JPG, PNG, BMP, TIFF, HEIF, DOCX, PPTX, XLSX [10]learn.microsoft.com/en-us/azure/ai-services/document-intelligence/service-limits“| Document types supported | Read | Layout | Prebuilt models | Custom models | Add-on capabilities | | --- | --- | --- | --- | --- | --- | | PDF | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ | | Images: `JPEG/JPG`, `PNG`, `BMP`, `TIFF`, `HEIF` | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ | | Microsoft Office: `DOCX`, `PPTX`, `XLS` | ✔️ | ✔️ | ✖️ | ✖️ | ✖️ |”

Output types

JSON, Searchable PDF [11]learn.microsoft.com/en-us/rest/api/aiservices/document-models/analyze-document“AnalyzeOutputOption ... | pdf | Generate searchable PDF output. | ... DocumentContentFormat ... | text | Plain text representation ... | markdown | Markdown representation of the document content with section headings, tables, etc. |”learn.microsoft.com/en-us/azure/ai-services/document-intelligence/faq“Azure Document Intelligence in Foundry Tools is a cloud-based service that uses machine-learning models to extract key/value pairs, text, and tables from your documents. The returned result is a structured JSON output.”

Webhooks

✗ No [12]learn.microsoft.com/en-us/azure/ai-services/document-intelligence/service-limits“If your application returns Response Code 429 (*Too many requests*) you are over the threshold for one or more of the transactions per second limits ... In general, we recommend not calling the get analyze response more than once every 2 seconds for a corresponding POST request. The `analyze` response also contains a **retry-after** header”

Sandbox / test mode

✗ No

SDK languages

C# / .NET, Java, JavaScript / TypeScript, Python [13]learn.microsoft.com/en-us/azure/ai-services/document-intelligence/faq“Document Intelligence offers the latest development options within the following platforms: REST API ... C#/.NET ... Java ... JavaScript/TypeScript ... Python”learn.microsoft.com/en-us/azure/ai-services/document-intelligence/versioning/sdk-overview-v4-0“Document Intelligence SDK supports the following languages and platforms: | .NET/C# → 1.0.0 (GA) | ... | Java → 1.0.0 (GA) | ... | JavaScript → 1.0.0 (GA) | ... | Python → 1.0.0 (GA) |”

MCP server

✗ No [14]learn.microsoft.com/en-us/azure/ai-services/document-intelligence/faq

SOC 2

SOC 2 Type II [15]learn.microsoft.com/en-us/azure/compliance/offerings/offering-soc-2“Microsoft Azure, Dynamics 365, and other Microsoft cloud services undergo rigorous independent third-party SOC 2 Type 2 audits conducted by a reputable certified public accountant (CPA) firm.”azure.microsoft.com/en-us/blog/cognitive-services-certifications-and-availability/

HIPAA

✓ Yes [16]learn.microsoft.com/en-us/azure/compliance/offerings/offering-hipaa-us“Azure has enabled the physical, technical, and administrative safeguards required by HIPAA and the HITECH Act inside the in-scope Azure services, and offers a HIPAA BAA as part of the Microsoft Product Terms (formerly Online Services Terms) to all customers who are covered entities or business associates under HIPAA.”learn.microsoft.com/en-us/azure/compliance/offerings/offering-hipaa-us“Microsoft will enter into BAAs with its covered entity and business associate customers.”

GDPR

✓ Yes [17]learn.microsoft.com/en-us/legal/cognitive-services/document-intelligence/data-privacy-security“This article provides details regarding how Document Intelligence processes your data. Document Intelligence is designed with compliance, privacy, and security in mind.”learn.microsoft.com/en-us/compliance/regulatory/gdpr

ISO 27001

✓ Yes [18]learn.microsoft.com/en-us/azure/compliance/offerings/offering-iso-27001“Microsoft Azure, Dynamics 365, and other Microsoft online services undergo regular independent third-party audits for ISO/IEC 27001 compliance.”azure.microsoft.com/en-us/blog/cognitive-services-certifications-and-availability/

PCI DSS

✗ No [19]azure.microsoft.com/en-us/explore/trusted-cloud/compliance/

Published SLA

✓ Yes [20]learn.microsoft.com/en-us/azure/ai-services/document-intelligence/service-limits“For **Free (F0)** pricing tier see also monthly allowances at the pricing page.”azure.microsoft.com/en-us/support/legal/sla/cognitive-services/v1_1/

Rate limits

Free (F0): 1 TPS Analyze, 1 TPS GET operations, 1 TPS model management, 1 TPS list operations; max doc size 4 MB; max pages per analysis 2. Standard (S0): 15 TPS Analyze (default, adjustable), 50 TPS GET operations (default, adjustable), 5 TPS model management (default, adjustable), 10 TPS list operations (default, adjustable); max doc size 500 MB; max pages per analysis 2,000. (Source: https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/service-limits) [21]learn.microsoft.com/en-us/azure/ai-services/document-intelligence/service-limits“| Quota | Free (F0) | Standard (S0) | | **Analyze transactions Per Second limit** | 1 | 15 (default value) | | **Get operations Per Second limit** | 1 | 50 (default value) | | **Max document size** | 4 MB | 500 MB | | **Max number of pages (Analysis)** | 2 | 2000 |”

Known restrictions

Free (F0) tier limits document analysis to only the first two pages per request, Free (F0) tier max document size is 4 MB vs 500 MB on Standard, PDF and TIFF max 2,000 pages (Standard tier), Image dimensions must be between 50x50 pixels and 10,000x10,000 pixels, Minimum text height for extraction is 12 pixels for a 1024x768 image, Password-locked PDFs must have password removed before submission, Microsoft Office files (DOCX, PPTX, XLSX) are only supported by Read and Layout models, not prebuilt or custom extraction models, No webhook/callback support; async operations require polling, Data and results are temporarily stored in Azure Storage in the same region for 24 hours, then deleted, Custom neural model free training capped at 10 hours/month (v4.0); additional training billed per hour, Disconnected container support limited to custom and invoice models, Copying models across cloud environments (e.g., public cloud to Azure Government) is not supported [22]learn.microsoft.com/en-us/azure/ai-services/document-intelligence/service-limits“| Microsoft Office: `DOCX`, `PPTX`, `XLS` | ✔️ | ✔️ | ✖️ | ✖️ | ✖️ | ✔️ = supported ✖️ = Not supported”learn.microsoft.com/en-us/legal/cognitive-services/document-intelligence/data-privacy-security“Analyze response is stored for 24 hours from when the operation completes for retrieval. Customers can delete the analysis response at any time by utilizing the Delete Analyze Result API.”

• Docs
• llms.txt

Docs rendering: static · llms.txt present

API style

rest

Base URL

https://{endpoint}/documentintelligence

Version

2024-11-30

Versioning

url

Stability

ga

Auth methods

api_key, oauth2

Idempotency keys

✗ No

Error format

vendor-specific (JSON: {error: {code, message, details, innererror}})

Rate limit

15 / second

SDKs

• C# / .NET Azure.AI.DocumentIntelligence · repo
• Java com.azure:azure-ai-documentintelligence · repo
• JavaScript / TypeScript @azure-rest/ai-document-intelligence · repo
• Python azure-ai-documentintelligence · repo

• Auth docs
• Quickstart
• Deprecation policy

Launched

2019-01-01

GA

2020-08-01

• Amazon Textract

  "Automatically extract printed text, handwriting, layout elements, and data from any document"

  Usage · public pricing · self-serve

• Veryfi

  "Documents into Data - securely, in seconds"

  Hybrid · free tier · public pricing · self-serve

• Google Document AI

  "A document processing and understanding platform that takes unstructured data from documents and transforms it into structured data, making it easier to understand, analyze, and consume."

  Usage · public pricing · self-serve

• Nanonets

  "AI Agents for Enterprise Data Processing."

  Usage · public pricing · self-serve

• Extend

  "Turn documents into high quality data"

  Hybrid · public pricing · self-serve

• Mindee

  "Turn your document data into structured JSON with high-reliability. Zero model training required."

  Hybrid · public pricing · self-serve

Azure AI Document Intelligence alternatives · Azure AI Document Intelligence vs Amazon Textract · All OCR & Document Parsing APIs APIs

Each field above carries a numbered source - hover for a preview, click to jump here.

1. ↑Description: learn.microsoft.com · learn.microsoft.com
2. ↑Pricing model: learn.microsoft.com · azure.microsoft.com
3. ↑Published pricing: learn.microsoft.com · azure.microsoft.com
4. ↑Free tier: learn.microsoft.com · azure.microsoft.com · learn.microsoft.com
5. ↑Self-serve signup: learn.microsoft.com
6. ↑Enterprise plan: learn.microsoft.com · azure.microsoft.com
7. ↑Supported actions: learn.microsoft.com · learn.microsoft.com · learn.microsoft.com
8. ↑Regions: learn.microsoft.com · learn.microsoft.com
9. ↑Languages: learn.microsoft.com · learn.microsoft.com
10. ↑Input types: learn.microsoft.com
11. ↑Output types: learn.microsoft.com · learn.microsoft.com
12. ↑Webhooks: learn.microsoft.com
13. ↑SDK languages: learn.microsoft.com · learn.microsoft.com
14. ↑MCP server: learn.microsoft.com
15. ↑SOC 2: learn.microsoft.com · azure.microsoft.com
16. ↑HIPAA: learn.microsoft.com · learn.microsoft.com
17. ↑GDPR: learn.microsoft.com · learn.microsoft.com
18. ↑ISO 27001: learn.microsoft.com · azure.microsoft.com
19. ↑PCI DSS: azure.microsoft.com
20. ↑Published SLA: learn.microsoft.com · azure.microsoft.com
21. ↑Rate limits: learn.microsoft.com
22. ↑Known restrictions: learn.microsoft.com · learn.microsoft.com

Every field change, who made it, and when - from our audited data pipeline and editors.

1. 2026-06-15 Score Agent Friendliness: 25 → 45
2. 2026-06-14 Robots Allows Agents: (none) → Yes
3. 2026-06-14 Has Structured Data: (none) → Yes
4. 2026-06-14 Capabilities: {} → {"tables":true,"id_documents":true,"custom_models":true,"agentic_output":true,"…
5. 2026-06-14 Summary Md: (none) → Azure AI Document Intelligence is a machine-learning OCR and document processin…
6. 2026-06-14 Score Docs Quality: 0 → 25
7. 2026-06-14 Best For: Prototypes and side projects - free to start, no sales call, Regulated or enter… → Prototypes and side projects - free to start, no sales call, Regulated or enter…
8. 2026-06-14 Score Agent Friendliness: 10 → 25
9. 2026-06-14 Llms Txt Present: (none) → Yes
10. 2026-06-14 Llms Txt URL: (none) → https://azure.microsoft.com/llms.txt
11. 2026-06-14 Rendering: (none) → static
12. 2026-06-14 Docs URL: (none) → https://azure.microsoft.com/developer
13. 2026-06-14 Score Agent Friendliness: (none) → 10
14. 2026-06-14 Score Pricing Transparency: (none) → 100
15. 2026-06-14 Best For: (none) → Prototypes and side projects - free to start, no sales call, Regulated or enter…
16. 2026-06-14 Scoring Methodology: (none) → Scores are computed deterministically from this profile's published, sourced fi…
17. 2026-06-14 Score Trust Readiness: (none) → 90
18. 2026-06-14 Score Procurement Friction: (none) → 100
19. 2026-06-14 Score Docs Quality: (none) → 0
20. 2026-06-14 Score Setup Speed: (none) → 85
21. 2026-06-14 Last Verified At: 2026-06-13T00:00:00.000Z → 2026-06-14T00:00:00.000Z
22. 2026-06-14 Starting Price Usd: 1.5 → 1.5
23. 2026-06-14 SDK Packages: C# / .NET, Java, JavaScript / TypeScript, Python → C# / .NET, Java, JavaScript / TypeScript, Python
24. 2026-06-13 Enterprise Plan Available: set to Yes
25. 2026-06-13 SOC 2: set to type_2
26. 2026-06-13 GDPR: set to Yes
27. 2026-06-13 ISO 27001: set to Yes
28. 2026-06-13 PCI DSS: set to No
29. 2026-06-13 SLA Published: set to Yes
30. 2026-06-13 SLA URL: set to https://azure.microsoft.com/en-us/support/legal/sla/cognitive-services/
31. 2026-06-13 Data Retention Policy URL: set to https://learn.microsoft.com/en-us/legal/cognitive-services/document-intelligenc…
32. 2026-06-13 Documented Rate Limits: set to Free (F0): 1 TPS Analyze, 1 TPS GET operations, 1 TPS model management, 1 TPS l…
33. 2026-06-13 Rate Limit Requests: set to 15
34. 2026-06-13 Rate Limit Window: set to second
35. 2026-06-13 Known Restrictions: set to Free (F0) tier limits document analysis to only the first two pages per request…
36. 2026-06-13 Auth Methods: set to api_key, oauth2
37. 2026-06-13 Auth Docs URL: set to https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/versi…
38. 2026-06-13 API Style: set to rest
39. 2026-06-13 Base URL: set to https://{endpoint}/documentintelligence
40. 2026-06-13 API Version: set to 2024-11-30
41. 2026-06-13 Versioning Scheme: set to url
42. 2026-06-13 Stability: set to ga
43. 2026-06-13 Deprecation Policy URL: set to https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/train…
44. 2026-06-13 Quickstart URL: set to https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/quick…
45. 2026-06-13 Idempotency Supported: set to No
46. 2026-06-13 Error Format: set to vendor-specific (JSON: {error: {code, message, details, innererror}})
47. 2026-06-13 Requires Verification: set to No
48. 2026-06-13 Starting Price Usd: set to 1.5
49. 2026-06-13 Price Basis: set to 1,000 pages
50. 2026-06-13 Free Tier Limit: set to 500 pages/month

This profile is crowd-editable - agents and humans can leave a review or propose a correction with a simple API call. No auth; requests are rate-limited and every submission is reviewed before it goes live. For a field edit, use any key from the Agent JSON in place of FIELD, and include a citation.

curl -X POST https://apio.sh/api/feedback/azure-document-intelligence \
  -H 'Content-Type: application/json' \
  -d '{"kind":"review","rating":5,"body":"Your experience with this API…"}'

curl -X POST https://apio.sh/api/suggest/azure-document-intelligence/FIELD \
  -H 'Content-Type: application/json' \
  -d '{"value":"corrected value","citations":[{"url":"https://source.example/page","excerpt":"supporting quote"}],"note":"what changed and why"}'

All the ways to contribute →