Skip to the content
Know your tech before you buy it. Makers: get listed from $49/mo

Amazon Textract AnalyzeExpense

aws.amazon.com

  • Free plan
  • Web
  • API
  • Self-hosted
7.6 Club score Visit aws.amazon.com

What Amazon Textract AnalyzeExpense is

Amazon Textract AnalyzeExpense is an API and web service for extracting financial text and data from invoices and receipts. Results can include grouped line items and summary fields such as items purchased, prices, receipt headers, and vendor names. The API can normalize field names and column headers, helping downstream applications compare information across documents. It can also identify a vendor from a logo and extract items, quantities, and prices when those details lack labels. Documents can be sent as image bytes or as an Amazon S3 object. AWS advises using PDF, JPG, or PNG files, and invoice and receipt processing is English only. AnalyzeExpense runs synchronously; asynchronous invoice and receipt analysis uses StartExpenseAnalysis and GetExpenseAnalysis. AWS lists a free tier for new customers for three months, up to 100 pages a month. The stated rate is $0.01 per page for the first million pages per month in US West (Oregon), then $0.008 per page; custom high-volume pricing is available.

Who it suits

AnalyzeExpense is for developers and organizations that need invoice or receipt data extracted for downstream applications. Its normalized fields may help when comparing information across documents.

Good to know, and what to watch

  • Returns line-item groups and summary fields.
  • Can identify vendors from logos.
  • Accepts image bytes or Amazon S3 objects.
  • Supports asynchronous processing through named API operations.
  • Invoice and receipt processing is English only.
  • Supported inputs are PDF, JPG, or PNG.
  • The listed per-page rate varies after one million pages.

AWS Free Tier

Free

AWS Free Tier — Analyze Expense

Free

Analyze Expense API

$0.01/mo

Analyze Expense API — first 1 million pages

$0.01/mo

Getting started

  1. Open the Amazon Textract website
  2. Use the AWS Free Tier or Analyze Expense API plan
  3. Prepare a PDF, JPG, or PNG document up to 500 MB
  4. Provide the document as image bytes or an Amazon S3 object
  5. Call AnalyzeExpense synchronously, or use StartExpenseAnalysis and GetExpenseAnalysis asynchronously
  6. Connect through an AWS SDK, API, or web service

Limits to check

The Free Tier lasts three months for new AWS customers and covers up to 100 pages per month. The listed paid rate is $0.01 per page for the first 1 million pages monthly in US West (Oregon), then $0.008 per page; high-volume custom pricing is available.

The Club's review

Amazon Textract AnalyzeExpense is an AWS service for extracting financial data from invoices and receipts, suited to teams building document intake into applications. Its structured fields and line items can reduce the work of reconciling varied documents, while English-only processing and per-page charges narrow its fit.

Overview

AnalyzeExpense returns summary fields and line-item groups, including vendor names, receipt headers, purchased items, and prices. It can normalize field names and column headers so a receiving application can compare documents that use different labels. It can also identify a vendor from a logo and extract items, quantities, and prices when the document has no labels or column headers. That combination is useful for expense and accounts-payable workflows where invoice layouts vary.

Documents can be sent as image bytes or from Amazon S3. Processing is synchronous; asynchronous analysis uses StartExpenseAnalysis and GetExpenseAnalysis. AWS advises using supported PDF, JPG, or PNG files, and caps file size at 500 MB.

Key features

  • Structured financial data: Summary fields and line items give downstream systems information to work with, rather than only a block of recognized text.
  • Normalized fields: Common field names and column headers can make comparisons across differently formatted invoices and receipts more practical.
  • Unlabeled content: Logo-based vendor identification and extraction without column headers can help when documents have inconsistent or sparse layouts.
  • API and developer support: The service offers synchronous and asynchronous processing, with SDKs for C#, C++, Go, Java, JavaScript, Kotlin, PHP, Python, and Ruby.

The language restriction is material: invoice and receipt processing is English only. Teams handling documents in other languages should choose a different fit.

Pricing

The AWS Free Tier costs nothing for three months for new AWS customers and includes up to 100 AnalyzeExpense pages per month. That is a limited way for eligible new customers to try a small volume; it is not a continuing free plan.

The Analyze Expense API plan is $0.01 a month, billed at $0.01 per page for the first 1 million pages per month in US West (Oregon), then $0.008 per page after 1 million. It is pay per page processed, with custom pricing available for high volumes. This gives low-volume users a direct usage-based cost, while large workloads may need a custom quote. Buyers should estimate page volume, since document length affects the charge.

Platforms

AnalyzeExpense is available through an API and on the web. It supports image input and Amazon S3 objects, and offers asynchronous processing for workflows that do not use synchronous analysis.

Who it's for

It suits organizations building invoice, receipt, expense, or accounts-payable intake into software, particularly when they need structured line items and consistent fields across documents. AWS users can also draw on its IAM controls, CloudTrail logging and monitoring, VPC endpoints through AWS PrivateLink, and documented data protection and resilience controls.

Privacy terms deserve attention before processing sensitive documents. AWS says inputs may be used to maintain and improve Textract and related AI technologies. It describes encryption in transit and at rest, and offers an Organizations opt-out policy. Processed content is encrypted and stored in the AWS region in use, though some content may be stored in another region for service improvement unless the customer opts out. Textract is listed as HIPAA eligible and compliant with PCI, ISO, and SOC programs; buyers should assess those controls against their own requirements.

Pros and cons

  • Pro: Extracts summary data and line items, including some unlabeled content, which can help automate intake from variable invoice and receipt formats.
  • Pro: Normalized fields support comparisons across documents, while API access and multiple SDKs suit application integration.
  • Pro: VPC endpoints allow API calls from within a VPC without using the public internet.
  • Con: Invoice and receipt processing is English only, ruling it out for multilingual document queues.
  • Con: Per-page pricing means costs scale with processed volume; the free tier is limited to three months and 100 pages monthly for new AWS customers.
  • Con: AWS's stated data-use terms may not suit every organization handling sensitive financial records.

Alternatives

For a broader OCR API software shortlist, compare other tools. The Veryfi Invoices OCR API has a free plan and a $500/mo minimum commitment for its Starter plan, so consider it when its freemium option or stated invoice pricing better fits your needs. OCR.space offers a free plan with 25,000 requests per month, but caps files at 1 MB and PDFs at three pages; it may fit smaller files and workloads that can stay within those limits. Dynamsoft Label Recognizer uses developer-seat development licenses with separate runtime and deployment licenses, so compare it when that licensing model suits your project.

Tesseract OCR is a free, open-source OCR engine under Apache License 2.0. EasyOCR is a free option for Linux, macOS, and Windows. Microblink BlinkID offers custom plans tailored to business needs. PaddleOCR has an official API free tier with a daily parsing limit of 20,000 pages. docTR is a free open-source Python library requiring Python 3.11 or higher.

Readers can also browse AI OCR software, AI document processing software, intelligent document processing software, and AI PDF tools.

Verdict

Choose Amazon Textract AnalyzeExpense when you need invoice and receipt data, including line items and some unlabeled fields, integrated into an application. Its normalized output and AWS connectivity make it a practical fit for structured financial intake. Look elsewhere if your documents are not in English, if per-page pricing does not suit your volume, or if AWS's data-use terms do not meet your privacy requirements.

The verdict

AnalyzeExpense is focused on financial data extraction from invoices and receipts, including some unlabeled fields. Buyers should account for its English-only processing and per-page pricing structure.

Questions people ask

Is AnalyzeExpense free?

There is no ongoing free plan. New AWS customers can use the AWS Free Tier for three months, with up to 100 Analyze Expense pages per month.

What does it extract?

Results can include line-item groups, purchased items, prices, receipt headers, vendor names, quantities, and normalized field or column names.

Which file types and languages are supported?

AWS advises PDF, JPG, or PNG files, supplied as image bytes or an Amazon S3 object. Invoice and receipt processing is English only.

How is AnalyzeExpense priced?

The listed API plan costs $0.01 per page for the first 1 million pages per month in US West (Oregon), then $0.008 per page. High-volume custom pricing is available.

Can it process documents asynchronously?

Yes. Synchronous processing is available, while asynchronous invoice and receipt analysis uses StartExpenseAnalysis and GetExpenseAnalysis.

What programming languages have SDK support?

SDKs are listed for C#, C++, Go, Java, JavaScript, Kotlin, PHP, Python, and Ruby.

What the maker publishes

Access controls and monitoring
Textract security documentation covers IAM, CloudTrail logging and monitoring, data protection, resilience, and VPC endpoints. source
API surface
The public API includes AnalyzeExpense, StartExpenseAnalysis, GetExpenseAnalysis, AnalyzeDocument, AnalyzeID, AnalyzeLending, adapter-management and text-detection operations. source
Asynchronous expense processing
StartExpenseAnalysis begins asynchronous invoice or receipt processing and GetExpenseAnalysis retrieves results after completion. source
CLI and console
Textract can be used through the AWS Management Console, AWS CLI and API. source
Compliance
AWS lists Textract as HIPAA eligible and compliant with PCI, ISO, and SOC programs. source
Compliance
AWS states that Textract is covered by HIPAA, SOC, ISO and PCI compliance programs, subject to applicable conditions. source
Custom Queries
Custom Queries adapters can be trained from as few as ten annotated sample documents in the AWS Console. source
Deployment model
Textract is delivered as an AWS-hosted service accessed through regional HTTPS endpoints; AWS does not provide a self-hosted Textract server. source
Documentation depth
AWS documentation includes a conceptual Developer Guide, detailed API Reference, getting-started procedures, quotas, IAM, encryption and code examples. source
Expense analysis
AnalyzeExpense synchronously analyzes invoices and receipts and returns line-item groups and summary fields in JSON. source
Extracted data
Results include line item groups and summary fields, such as purchased items, prices, receipt headers, and vendor names. source
File and size limits
Supported formats are JPEG, PNG, PDF and TIFF; synchronous requests allow one-page PDF/TIFF files up to 10 MB, while asynchronous PDF/TIFF files can be up to 500 MB and 3,000 pages. source
Forms
The service extracts related key-value pairs from document forms while preserving their context. source
Identity documents
AnalyzeID extracts information such as expiry date, birth date, names and addresses from supported identity documents without templates. source
Independent review tradeoff
OCR Vendors rates Textract 7.4/10, praising low per-page cost and AWS integrations while citing AWS lock-in, required expertise, extra-cost support and fewer prebuilt processors than Google. source
Independent test limitation
An independent review found Textract’s unstructured text extraction accurate and inexpensive but reported poor forms accuracy and slower asynchronous PDF workflows requiring S3. source
Input
A document can be supplied as image bytes or as an Amazon S3 object. source
Integrations
AWS lists robotic-process-automation partners Blue Prism, Ripcord and UiPath, plus service and software partners including Accenture, Deloitte, Box and PwC. source
Language support limit
Text detection supports English, French, German, Italian, Portuguese and Spanish; handwriting, invoices, receipts, identity documents and Queries are English-only. source
Lending
Analyze Lending classifies, splits and extracts information from mortgage application document packages and can summarize signature detection. source
Licence
Textract is a proprietary AWS cloud service rather than an open-source package with a redistributable software licence. source
Limit: cost and AWS complexity
G2 reviewers repeatedly complain that large-volume processing is expensive and that integration requires AWS infrastructure knowledge. source
Limit: Cyrillic support
A Gartner Peer Insights dislike states that Textract does not support Cyrillic characters. source
Limit: document layout
Textract does not support vertically aligned text, XFA PDFs or password-protected PDFs. source

Checked against the maker's pages on 15 Oct 2026.