Amazon Textract is a machine learning (ML) service that uses optical character recognition (OCR) to automatically extract text, handwriting, and data from scanned documents such as PDFs. With Amazon Textract, you pay only for what you use. There are no minimum fees and no upfront commitments. Amazon Textract charges only for pages processed whether you extract text, text with tables, and/or form data. See the FAQ for additional details about pages and acceptable use of Amazon Textract.
Amazon Textract has four APIs: Detect Document Text API, Analyze Document API, Analyze Expense API, and Analyze ID API.
Detect Document Text API uses optical character recognition (OCR) technology to extract text and handwriting from a document. In the US West (Oregon) Region, you pay $0.0015 per page for the first 1 million pages and $0.0006 per page for over 1 million pages.
Analyze Document API has two functions, forms and tables, with different pricing levels.
- Analyze Document API for forms uses OCR technology to extract text and handwriting from a document. It also extracts data such as key-value pairs (for example, “First Name” and associated value “Jane Smith”). In the US West (Oregon) Region, you pay $0.05 per page for the first 1 million pages and $0.04 per page for over 1 million pages.
- Analyze Document API for tables uses OCR technology to extract text and handwriting from a document. It also extracts tabular or table data organized in columns and rows. In the US West (Oregon) region, you pay $0.015 per page for the first 1 million pages and $0.01 per page for over 1 million pages.
Free Tier
As part of the AWS Free Tier, you can get started with Amazon Textract for free. The Free Tier lasts for three months, and new AWS customers can analyze up to 1,000 pages per month using the Detect Document Text API and up to 100 pages per month using the Analyze Document API, Analyze Expense API, or Analyze ID API.
Amazon Textract API pricing
Detect Document Text API (OCR)
Analyze Document API for pages with tables
*Tables are collections of related data that are visually organized into columns and rows. For example, an operational log that tracks the daily output of a factory.
Analyze Document API for pages with forms
*Forms are a collection of independent keys and values that happen to be on the same page (for example, W2).
Analyze Document API for pages with tables and forms
Analyze Expense API for invoices and receipts
Analyze ID API
Pricing examples outside the free tier
Pricing example 1 - Detect Document Text API
Let’s say you want to extract the text from 100,000 pages of research reports using the Detect Document Text API. The pricing per page in US West (Oregon) Region for the first 1 million pages is $0.0015, so for processing 100,000 pages, the total cost per month would be $150.
Total pages processed = 100,000
Price per page = $0.0015
Total charge per month = $0.0015*100,000 = $150
Pricing example 2 - Detect Document Text API
Let’s say you want to extract the text from 2 million pages of research reports using the Detect Document Text API. The pricing per page in the US West (Oregon) Region for the first 1 million pages is $0.0015, and pages after 1 million are $0.0006, so for processing 2 million pages, the total cost would be $2,100.
Total pages processed = 2,000,000
Price per page = $0.0015 for first 1 million and $0.0006 for pages after 1 million
Total charge per month = $0.0015*1,000,000 + $0.0006 * 1,000,000 = $1,500 + $600 = $2,100
Pricing example 3 - Analyze Document API – Forms and Tables
Let’s assume you want to extract the text and structured data from 5,000 pages of tax forms using the Analyze Document API. The pricing per page in the US West (Oregon) Region for 1 million pages with tables is $0.015, and with forms is $0.05, for a total of $325. See the calculation below:
Total pages processed = 5,000 pages
Price for page with table = $0.015
Price for page with form (key-value pair) = $0.05
Total charge = $0.015*5,000 + $0.05 *5,000 = $75 + $250 = $325
Pricing example 4 - Analyze Document API – Forms and Tables
Let’s say you want to extract text, forms, and tables from 2 million pages of tax forms using the Analyze Document API. The pricing per page in the US West (Oregon) Region for 1 million pages with tables is $0.015, and $0.01 per page after 1 million pages. Pricing for pages with forms is $0.05 for 1 million pages, and $0.04 per page after 1 million. The total cost would be $115,000.
Total pages processed = 2,000,000 pages
Price for page with form (key-value pair) = $0.05 for the first 1 million and $0.04 for the next 1 million
Total charge = $0.015*1,000,000 + $0.01*1,000,000 + $0.05*1,000,000 + $0.04*1,000,000 = $15,000 + $10,000 + 50,000 + 40,000 = $115,000
Pricing example 5 - Analyze Expense API
Let’s say you want to extract data from 100,000 invoices using the Analyze Expense API. The pricing per page in the US West (Oregon) region for 1 million pages is $0.01, and you process 100,000 invoices. The total cost would be $1,000.
Total pages processed = 100,000
Price per page = $0.01
Total charge per month = $0.01*100,000 = $1,000
Pricing example 6 - Analyze Expense API
Let’s say you want to extract data from 1.5 million invoices using the Analyze Expense API. The pricing per page in the US West (Oregon) Region for 1 million pages is $0.01 per page and $0.008 per page after 1 million. The total cost would be $14,000.
Total pages processed = 1,500,000
Price per page = $0.01 for the first 1 million and $0.008 for the next 500,000
Total charge per month = $0.01 * 1,000,000 + $0.008 * 500,000 = $14,000
Pricing example 7 – Analyze ID API
Let’s say you want to extract information from 100,000 identity documents using the Analyze ID API. The pricing per page in the US West (Oregon) Region for 100,000 pages is $0.025 per page for up to 100,000 pages. The total cost would be $2,500.
Total pages processed = 100,000
Price per page = $0.025
Total charge per month = $0.025 * 100,000 = $2,500
Pricing example 8 – Analyze ID API
Let’s say you want to extract information from 600,000 identity documents using the Analyze ID API. The pricing per page in the US West (Oregon) Region for 100,000 pages is $0.025 per page and $0.01 per page after 100,000. The total cost would be $17,500.
Total pages processed = 600,000
Price per page = $0.025 for the first 00,000 and $0.01 for the next 500,000
Total charge per month = $0.025 * 100,000 + $0.01 * 500,000 = $7,500
Learn more about how Amazon Textract extracts text and structured data from virtually any document.
Get started building with Amazon Textract in the AWS Management Console.
