Amazon Textract

Best for: Regulated or enterprise workloads - compliance attestations and an enterprise plan; AI agents and automation - an agent-ready surface (MCP / llms.txt); Teams needing broad API coverage out of the box

Avoid if: You want to try it free before paying

• ███▒░░░░░░
  35 / 100
  Agent friendliness
• ████████▒░
  85 / 100
  Pricing transparency
• ██████░░░░
  60 / 100
  Setup speed
• ██▒░░░░░░░
  25 / 100
  Docs quality
• ████████▒░
  85 / 100
  Procurement ease
• ██████████
  100 / 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]docs.aws.amazon.com/textract/latest/dg/what-is.html“Low cost – With Amazon Textract, you only pay for the documents you analyze. There are no minimum fees or upfront commitments.”aws.amazon.com/textract/pricing/“Detect Document Text API — first 1M pages: $0.0015/page ... After 1M pages: $0.0006/page”

Published pricing

✓ Yes [3]aws.amazon.com/textract/pricing/“Detect Document Text API — First 1M pages: $0.0015/page; After 1M pages: $0.0006/page ... Analyze Document API - Forms: $0.05/page (first 1M) ... Analyze Lending API: $0.07/page (first 1M), $0.055/page (after)”

Free tier

✗ No [4]aws.amazon.com/textract/pricing/“Free Tier (3 months for new AWS customers): Detect Document Text API: 1,000 pages/month; Analyze Document API: 100-1,000 pages/month (varies by feature); Analyze Expense API: 100 pages/month; Analyze ID API: 100 pages/month; Analyze Lending API: 2,000 pages/month”aws.amazon.com/textract/faqs/“New AWS customers receive three months of complimentary access including: Detect Document Text (1,000 pages/month), Analyze Document with Signatures (1,000 pages/month), Analyze Expense API (100 pages/month), Analyze ID API (100 pages/month), and Analyze Lending API (2,000 pages/month).”

Free tier details

3-month time-limited trial for new AWS customers only: Detect Document Text 1,000 pages/month; Analyze Document (Signatures) 1,000 pages/month; Analyze Document (Forms/Tables/Layout/Queries) 100 pages/month; Analyze Expense 100 pages/month; Analyze ID 100 pages/month; Analyze Lending 2,000 pages/month. Not a perpetual free tier.

Self-serve signup

✓ Yes [5]docs.aws.amazon.com/textract/latest/dg/setting-up.html“To get started with AWS, you need an AWS account. For information about creating an AWS account, see Getting started with an AWS account in the AWS Account Management Reference Guide.”docs.aws.amazon.com/textract/latest/dg/getting-started.html“You can try the API by using the demonstration in the Amazon Textract console. For more information, see https://console.aws.amazon.com/textract/.”

Requires sales call

✗ No

Enterprise plan

✓ Yes [6]docs.aws.amazon.com/textract/latest/dg/what-is.html“Low cost – With Amazon Textract, you only pay for the documents you analyze. There are no minimum fees or upfront commitments. You can get started for free, and save more as you grow with our tiered pricing model.”docs.aws.amazon.com/textract/latest/dg/limits-quotas-explained.html“When requesting an increase to a default quota, there are several recommended best practices to follow. ... Contact AWS Support if you find that your average number of concurrent requests can't be managed by an Amazon SQS queue.”

• Receipts / invoices
• ID documents
• Table extraction
• Handwriting
• Custom models

Supported actions

DetectDocumentText, AnalyzeDocument (Forms, Tables, Queries, Signatures, Layout, Custom Queries), AnalyzeExpense, AnalyzeID, StartDocumentTextDetection, StartDocumentAnalysis, StartExpenseAnalysis, StartIDDocumentAnalysis, GetDocumentTextDetection, GetDocumentAnalysis, GetExpenseAnalysis, GetIDDocumentAnalysis, StartLendingAnalysis, GetLendingAnalysis, GetLendingAnalysisSummary, CreateAdapter, CreateAdapterVersion, DeleteAdapter, DeleteAdapterVersion, UpdateAdapter, GetAdapter, GetAdapterVersion, ListAdapters, ListAdapterVersions [7]docs.aws.amazon.com/textract/latest/APIReference/API_Operations.html“The following actions are supported: AnalyzeDocument, AnalyzeExpense, AnalyzeID, CreateAdapter, CreateAdapterVersion, DeleteAdapter, DeleteAdapterVersion, DetectDocumentText, GetAdapter, GetAdapterVersion, GetDocumentAnalysis, GetDocumentTextDetection, GetExpenseAnalysis, GetLendingAnalysis, GetLendingAnalysisSummary, ListAdapters, ListAdapterVersions, StartDocumentAnalysis, StartDocumentTextDetection, StartExpenseAnalysis, StartLendingAnalysis, UpdateAdapter”docs.aws.amazon.com/textract/latest/dg/what-is.html“Extract text, forms, and tables from documents with structured data, using the Amazon Textract Document Analysis API. Specify and extract information from documents using the Queries feature within the Amazon Textract Analyze Document API.”

Regions

US East (N. Virginia) us-east-1, US East (Ohio) us-east-2, US West (N. California) us-west-1, US West (Oregon) us-west-2, Asia Pacific (Mumbai) ap-south-1, Asia Pacific (Seoul) ap-northeast-2, Asia Pacific (Singapore) ap-southeast-1, Asia Pacific (Sydney) ap-southeast-2, Canada (Central) ca-central-1, Europe (Frankfurt) eu-central-1, Europe (Ireland) eu-west-1, Europe (London) eu-west-2, Europe (Paris) eu-west-3, Europe (Spain) eu-south-2, AWS GovCloud (US-East) us-gov-east-1, AWS GovCloud (US-West) us-gov-west-1 [8]docs.aws.amazon.com/general/latest/gr/textract.html“US East (Ohio) us-east-2 ... US East (N. Virginia) us-east-1 ... US West (N. California) us-west-1 ... US West (Oregon) us-west-2 ... Asia Pacific (Mumbai) ap-south-1 ... Asia Pacific (Seoul) ap-northeast-2 ... Asia Pacific (Singapore) ap-southeast-1 ... Asia Pacific (Sydney) ap-southeast-2 ... Canada (Central) ca-central-1 ... Europe (Frankfurt) eu-central-1 ... Europe (Ireland) eu-west-1 ... Europe (London) eu-west-2 ... Europe (Paris) eu-west-3 ... Europe (Spain) eu-south-2 ... AWS GovCloud (US-East) us-gov-east-1 ... AWS GovCloud (US-West) us-gov-west-1”aws.amazon.com/textract/faqs/“Amazon Textract operates in: US East (Northern Virginia), US East (Ohio), US West (Oregon), US West (N. California), AWS GovCloud (US-West), AWS GovCloud (US-East), Canada (Central), EU (Ireland), EU (London), EU (Frankfurt), EU (Paris), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Seoul), and Asia Pacific (Mumbai).”

Languages

English, French, German, Italian, Portuguese, Spanish [9]docs.aws.amazon.com/textract/latest/dg/limits-document.html“Amazon Textract supports English, French, German, Italian, Portuguese, and Spanish text detection. Query detection is only available in English document detection.”aws.amazon.com/textract/faqs/“The service handles "printed text, forms and tables in English, German, French, Spanish, Italian and Portuguese." Handwriting detection, invoice/receipt processing, identity document analysis, and query features are "in English only."”

Input types

JPEG, PNG, PDF, TIFF [10]docs.aws.amazon.com/textract/latest/dg/limits-document.html“Operations support JPEG, PNG, PDF, and TIFF files. (JPEG 2000-encoded images within PDFs are supported). Textract does not support XFA based PDFs.”docs.aws.amazon.com/textract/latest/APIReference/API_DetectDocumentText.html“The input document must be in one of the following image formats: JPEG, PNG, PDF, or TIFF.”

Output types

JSON [11]docs.aws.amazon.com/textract/latest/APIReference/API_DetectDocumentText.html“DetectDocumentText returns the detected text in an array of Block objects. ... If the action is successful, the service sends back an HTTP 200 response. The following data is returned in JSON format by the service.”

Webhooks

✓ Yes [12]docs.aws.amazon.com/textract/latest/dg/async-notification-payload.html“Amazon Textract sends the status of an analysis request to an Amazon Simple Notification Service (Amazon SNS) topic. To get the notification from an Amazon SNS topic, use an Amazon SQS queue or an AWS Lambda function.”docs.aws.amazon.com/textract/latest/dg/api-async.html“The completion status of the request is published to an Amazon Simple Notification Service (Amazon SNS) topic. To get the completion status from the Amazon SNS topic, you can use an Amazon Simple Queue Service (Amazon SQS) queue or an AWS Lambda function.”

Sandbox / test mode

✗ No

SDK languages

Python, JavaScript/Node.js, Java, .NET, Go, Ruby, PHP [13]docs.aws.amazon.com/textract/latest/dg/setup-awscli-sdk.html“Download and install the AWS CLI and the AWS SDKs that you want to use. This guide provides examples for the AWS CLI, Java, and Python. For information about other AWS SDKs, see Tools for Amazon Web Services.”docs.aws.amazon.com/textract/latest/APIReference/API_DetectDocumentText.html“AWS SDK for .NET V4 ... AWS SDK for Go v2 ... AWS SDK for Java V2 ... AWS SDK for JavaScript V3 ... AWS SDK for PHP V3 ... AWS SDK for Python ... AWS SDK for Ruby V3”

MCP server

✗ No

SOC 2

SOC 2 Type II [14]aws.amazon.com/textract/faqs/“The service is "HIPAA eligible" and "compliant with PCI, ISO, and SOC."”

HIPAA

✓ Yes [15]aws.amazon.com/compliance/hipaa-eligible-services-reference/“Amazon Textract”aws.amazon.com/textract/faqs/“The service is "HIPAA eligible" and "compliant with PCI, ISO, and SOC."”

GDPR

✓ Yes [16]aws.amazon.com/compliance/gdpr-center/“AWS customers can use all AWS services to process personal data (as defined in the GDPR) that is uploaded to the AWS services under their AWS accounts (customer data) in compliance with the GDPR.”docs.aws.amazon.com/textract/latest/dg/data-protection.html“For information about data protection in Europe, see the AWS Shared Responsibility Model and GDPR blog post on the AWS Security Blog.”

ISO 27001

✓ Yes [17]aws.amazon.com/compliance/iso-certified/“Amazon Textract”aws.amazon.com/textract/faqs/“The service is "HIPAA eligible" and "compliant with PCI, ISO, and SOC."”

PCI DSS

✓ Yes [18]aws.amazon.com/textract/faqs/“The service is "HIPAA eligible" and "compliant with PCI, ISO, and SOC."”

Published SLA

✓ Yes [19]aws.amazon.com/textract/sla/“Availability is calculated for each 5-minute interval as the percentage of Requests processed that "do not fail with Errors and relate solely to the provisioned Amazon Textract function."”aws.amazon.com/textract/sla/“Service Credit Tiers: 99–99.9% uptime: 10% credit; Below 99% uptime: 25% credit; Below 95% uptime: 100% credit.”

Rate limits

Default TPS quotas vary by region and API. In US East (N. Virginia): DetectDocumentText sync=25 TPS, AnalyzeDocument sync=10 TPS, AnalyzeExpense sync=5 TPS, AnalyzeID sync=5 TPS; StartDocumentTextDetection async=15 TPS, StartDocumentAnalysis async=10 TPS, StartExpenseAnalysis async=5 TPS, StartLendingAnalysis async=5 TPS; Maximum concurrent async jobs=600 in us-east-1/us-west-2. Synchronous ops: max 15 queries per page; Asynchronous ops: max 30 queries per page. Limits are adjustable via AWS Service Quotas console. [20]docs.aws.amazon.com/general/latest/gr/textract.html“DetectDocumentText: US East (N. Virginia) 25 TPS, US West (Oregon) 25 TPS ... AnalyzeDocument: 10 TPS ... AnalyzeExpense: 5 TPS ... AnalyzeID: 5 TPS ... Maximum number of asynchronous jobs per account that can simultaneously exist: 600 (us-east-1, us-west-2)”docs.aws.amazon.com/textract/latest/dg/limits-quotas-explained.html“TPS quotas determine how often you can request that Textract process a new document. TPS quotas are unique to API, Synchronous or Asynchronous operations, and Region. ... Default quotas can be viewed or changed via the Service Quotas console.”

Known restrictions

Supported file formats: JPEG, PNG, PDF, TIFF only (no XFA-based PDFs), Sync operations: max 10 MB file size, PDF/TIFF limited to 1 page, Async operations: PDF/TIFF max 500 MB and 3,000 pages; JPEG/PNG max 10 MB, PDF max height/width: 40 inches and 9,000 points; cannot be password protected, Max image resolution: 10,000 pixels on all sides, Handwritten text recognition supported in English only, Query feature (natural language) available in English documents only, AnalyzeID supports US passports and US driver's licenses only, Vertical text (e.g., Japanese, Chinese vertical layout) not supported, Minimum text height: 15 pixels (equivalent to 8pt font at 150 DPI), Up to 15 queries per page (sync) and 30 queries per page (async), PCI DSS users must opt out of content use for service improvement via AWS Support, Max 10 adapters per account; max 10 adapter versions per month; max 3 in-progress adapter training jobs, Layout feature is free when used with the Tables feature [21]docs.aws.amazon.com/textract/latest/dg/limits-document.html“For synchronous operations, JPEG, PNG, PDF, and TIFF files have a limit of 10 MB in memory. PDF and TIFF files also have a limit of 1 page. For asynchronous operations ... PDF and TIFF files have a limit of 500 MB in memory and a limit of 3,000 pages.”docs.aws.amazon.com/textract/latest/dg/limits-document.html“Amazon Textract supports images with a resolution less than or equal to 10000 pixels on all sides. ... Amazon Textract does not support vertical text (text written vertically, as is common in languages like Japanese and Chinese) ... The minimum height for text to be detected is 15 pixels. At 150 DPI, this would be the same as 8 point font. ... AnalyzeID only supports US passports, and US driver's licenses.”

• Docs
• llms.txt
• Status page

Docs rendering: static · llms.txt present

API style

rest

Base URL

https://textract.{region}.amazonaws.com

Version

2018-06-27

Versioning

header

Stability

ga

Auth methods

hmac_signature

Idempotency keys

✓ Yes

Error format

vendor-specific

Rate limit

25 / second

SDKs

• Python boto3 · repo
• JavaScript/Node.js @aws-sdk/client-textract · repo
• Java software.amazon.awssdk:textract · repo
• .NET AWSSDK.Textract · repo
• Go github.com/aws/aws-sdk-go-v2/service/textract · repo
• Ruby aws-sdk-textract · repo
• PHP aws/aws-sdk-php · repo

• Auth docs
• Quickstart
• Webhook events
• Deprecation policy

Launched

2018-11-28

GA

2019-05-29

Notable customers

Change Healthcare, Roche, Elevance Health, Pennymac, Cox Automotive, The Washington Post, HelloSign, PitchBook

• 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

• Azure AI Document Intelligence

  "Azure Document Intelligence in Foundry Tools is a machine-learning based OCR and intelligent document processing service to automate extraction of key data from forms and documents."

  Usage · free tier · 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

Amazon Textract alternatives · Amazon Textract vs Veryfi · All OCR & Document Parsing APIs APIs

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

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

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

1. 2026-06-15 Best For: Regulated or enterprise workloads - compliance attestations and an enterprise p… → Regulated or enterprise workloads - compliance attestations and an enterprise p…
2. 2026-06-15 Score Docs Quality: 15 → 25
3. 2026-06-15 Score Agent Friendliness: 10 → 35
4. 2026-06-14 Llms Txt URL: (none) → https://docs.aws.amazon.com/llms.txt
5. 2026-06-14 Llms Txt Present: No → Yes
6. 2026-06-14 Robots Allows Agents: (none) → Yes
7. 2026-06-14 Has Structured Data: (none) → No
8. 2026-06-14 Capabilities: {} → {"tables":true,"handwriting":true,"id_documents":true,"custom_models":true,"rec…
9. 2026-06-14 Summary Md: (none) → Amazon Textract is an AWS document intelligence service that extracts printed t…
10. 2026-06-14 Score Docs Quality: 0 → 15
11. 2026-06-14 Llms Txt Present: (none) → No
12. 2026-06-14 Rendering: (none) → static
13. 2026-06-14 Status Page URL: (none) → https://status.aws.amazon.com
14. 2026-06-14 Docs URL: (none) → https://docs.aws.amazon.com
15. 2026-06-14 Scoring Methodology: (none) → Scores are computed deterministically from this profile's published, sourced fi…
16. 2026-06-14 Score Setup Speed: (none) → 60
17. 2026-06-14 Score Pricing Transparency: (none) → 85
18. 2026-06-14 Score Agent Friendliness: (none) → 10
19. 2026-06-14 Best For: (none) → Regulated or enterprise workloads - compliance attestations and an enterprise p…
20. 2026-06-14 Avoid If: (none) → You want to try it free before paying
21. 2026-06-14 Score Trust Readiness: (none) → 100
22. 2026-06-14 Score Procurement Friction: (none) → 85
23. 2026-06-14 Score Docs Quality: (none) → 0
24. 2026-06-14 SDK Packages: Python, JavaScript/Node.js, Java, .NET, Go, Ruby, PHP → Python, JavaScript/Node.js, Java, .NET, Go, Ruby, PHP
25. 2026-06-14 Starting Price Usd: 0.0015 → 0.0015
26. 2026-06-14 Last Verified At: 2026-06-13T00:00:00.000Z → 2026-06-14T00:00:00.000Z
27. 2026-06-14 Starting Price Usd: 0.0015 → 0.0015
28. 2026-06-14 SDK Packages: Python, JavaScript/Node.js, Java, .NET, Go, Ruby, PHP → Python, JavaScript/Node.js, Java, .NET, Go, Ruby, PHP
29. 2026-06-13 PCI DSS: set to Yes
30. 2026-06-13 SLA Published: set to Yes
31. 2026-06-13 SLA URL: set to https://aws.amazon.com/textract/sla/
32. 2026-06-13 Data Retention Policy URL: set to https://docs.aws.amazon.com/textract/latest/dg/data-protection.html
33. 2026-06-13 Documented Rate Limits: set to Default TPS quotas vary by region and API. In US East (N. Virginia): DetectDocu…
34. 2026-06-13 Rate Limit Requests: set to 25
35. 2026-06-13 Rate Limit Window: set to second
36. 2026-06-13 Known Restrictions: set to Supported file formats: JPEG, PNG, PDF, TIFF only (no XFA-based PDFs), Sync ope…
37. 2026-06-13 Auth Methods: set to hmac_signature
38. 2026-06-13 Auth Docs URL: set to https://docs.aws.amazon.com/textract/latest/dg/security-iam.html
39. 2026-06-13 API Style: set to rest
40. 2026-06-13 Base URL: set to https://textract.{region}.amazonaws.com
41. 2026-06-13 API Version: set to 2018-06-27
42. 2026-06-13 Versioning Scheme: set to header
43. 2026-06-13 Deprecation Policy URL: set to https://docs.aws.amazon.com/general/latest/gr/service-lifecycle.html
44. 2026-06-13 Quickstart URL: set to https://docs.aws.amazon.com/textract/latest/dg/getting-started.html
45. 2026-06-13 Idempotency Supported: set to Yes
46. 2026-06-13 Error Format: set to vendor-specific
47. 2026-06-13 Webhook Events URL: set to https://docs.aws.amazon.com/textract/latest/dg/async-notification-payload.html
48. 2026-06-13 Requires Verification: set to No
49. 2026-06-13 Starting Price Usd: set to 0.0015
50. 2026-06-13 Price Basis: set to page

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/aws-textract \
  -H 'Content-Type: application/json' \
  -d '{"kind":"review","rating":5,"body":"Your experience with this API…"}'

curl -X POST https://apio.sh/api/suggest/aws-textract/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 →