Enterprise document data extraction: fine-tuned OCR and large language models turn PDFs, Word, PowerPoint, and Excel into structured, reviewable data with explainable, source-traceable outputs.
TextMine is an enterprise Intelligent Document Processing (IDP) platform that turns unstructured documents into accurate, structured, reviewable data. Using proprietary, fine-tuned OCR and large language models (LLMs), TextMine extracts key fields, tables, and entities from PDFs, Word, PowerPoint, and Excel files, including scanned and complex layouts, without the brittle templates and manual rules that slow traditional document data extraction.
Every extraction is explainable and traceable to its source: outputs link back to the exact section of the original document, so reviewers can verify results in seconds. A built-in human-in-the-loop workflow lets teams validate, correct, and approve data before it flows downstream, combining automation speed with the accuracy critical documents demand. Results export as CSV or as a marked-up PDF, and the platform integrates into existing pipelines so extracted data reaches your systems of record automatically.
Built for teams working with contracts, agreements, and other high-stakes documents, TextMine reduces manual review, accelerates document automation, and improves data quality across the organization. From contract intelligence to bulk document ingestion, it helps legal, finance, and operations teams process large volumes of documents faster, with full transparency and confidence in the extracted data.
Highlights
Extract structured data from any document: fine-tuned OCR and large language models (LLMs) turn PDFs, Word, PowerPoint, and Excel, including scanned and complex layouts, into accurate structured data without brittle templates.
Explainable, review-ready results: every extraction is traceable to its exact source in the document, with a built-in human-in-the-loop workflow to validate and approve data before it flows downstream.
Automate high-stakes document workflows: Intelligent Document Processing (IDP) for contracts, agreements, and bulk ingestion that cuts manual review and pushes clean data into your systems via CSV, marked-up PDF, or integrations.
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing is based on the duration and terms of your contract with the vendor. This entitles you to a specified quantity of use for the contract duration. If you choose not to renew or replace your contract before it ends, access to these entitlements will expire.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
This listing offers one pricing option: the Enterprise Edition, billed per user under a contract. You pay based on the number of users who need access. This edition includes higher volume, advanced integrations, and priority support. Since there is a single dimension, your cost scales with how many users you add rather than by tier or usage. The contract sets your commitment term and user quantity up front.
Top-of-mind questions for buyers
What counts as one user for billing under the Enterprise Edition?
You are billed per user account that needs access to the platform. Each person you assign a role to counts as one user. Roles can be scoped by user group, workflow, document set, action, and review responsibility. Adding more people who need access increases your user count.
What do the higher volume and advanced integrations in this edition cover?
Higher volume means the edition supports larger document processing needs. Advanced integrations let you sync verified document context into finance, procurement, CRM, compliance, and data warehouse systems. You can also connect through a public API and expose governed context to agents. Priority support is included with this edition.
Does my cost change as document volume or usage grows within a term?
Your cost scales with the number of users you add, not by document volume or usage. The Enterprise Edition includes higher volume capacity, so processing more documents does not add a per-document charge. To lower cost, reduce user accounts; to expand access, add users.
textmine.com+1
Helpful?
Vendor refund policy
TextMine offers contract-based subscriptions billed for the agreed term. Contract fees are non-refundable once the contract term has begun, except in the case of a billing error or exceptional circumstances.
How can we make this page better?
Tell us how we can improve this page, or report an issue with this product.
Give us feedbackReport a problem with this product or seller
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA).
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Containers are lightweight, portable execution environments that wrap server application software in a filesystem that includes everything it needs to run. Container applications run on supported container runtimes and orchestration services, such as Amazon Elastic Container Service (Amazon ECS) or Amazon Elastic Kubernetes Service (Amazon EKS). Both eliminate the need for you to install and operate your own container orchestration software by managing and scheduling containers on a scalable cluster of virtual machines.
Version release notes
Slim customer parameters: only TenantSlug + role emails are shown; image versions, domain and provisioning endpoint are pinned internally. Same container images as 1.1.
Additional details
Usage instructions
Prerequisites: an AWS account with permissions to create VPC, ECS, RDS, ElastiCache, IAM and CloudFront resources.
Deployment: after subscribing, launch the provided CloudFormation template, provide TenantSlug + domain, and start the stack (~25-40 min). It provisions the full environment and pulls the images from AWS Marketplace.
Support: support@textmine.com.
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Be the first to review this product. We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.