Sold by: Upstage
Deployed on AWS
Free Trial
Parse PDFs, images, and scans into LLM-ready HTML. VLM-powered analysis for complex tables & charts.
Overview
Upstage Document Parse Enhanced is an all-in-one document intelligence API that transforms diverse file formats into structured HTML/Markdown. It combines the robust OCR and layout analysis of our Standard model with proprietary Vision Language Models (VLMs) for deep understanding.
Universal Document Support & VLM Precision:
-
Any Format, One Structure: Seamlessly processes PDFs, scanned images (JPEG, PNG, TIFF), and digital documents. Whether it's a blurry scan or a digital report, it unifies them into clean, structured HTML.
-
VLM-Powered Insight: Beyond reading text, it uses VLMs to "see" and interpret complex elements. It reconstructs borderless/nested tables, merges multi-page tables, and extracts numerical data from charts.
-
Visual Description: It automatically generates natural language captions for figures and diagrams, ensuring no visual context is lost in digitization.
Designed for Agentic RAG: Prioritizes semantic depth and data fidelity over raw speed (2x-10x processing time vs. Standard), delivering the rich context LLMs need.
Highlights
- **Format-Agnostic Parsing**: Handles everything from native PDFs to complex image scans. It identifies layouts (paragraphs, headers) and reconstructs reading order across formats. The Enhanced VLM engine then dives deep to merge split tables and interpret charts, ensuring consistent output quality regardless of the input file type.
- **Agentic RAG Ready**: By converting visual data (charts, figures) into text and merging fragmented tables, it preserves the full context often lost in standard OCR. This "semantically dense" output allows LLMs to reason over complex financial or scientific data effectively. It offers a trade-off of deeper processing time for unmatched data fidelity.
- **Key Tasks**: PDF & Image to HTML - VLM Document Understanding - Multi-page Table Merging - Chart-to-Data Conversion - Figure Captioning - Scanned Document OCR - Layout Analysis
Details
Sold by
Categories
Delivery method
Latest version
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
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
Free trial
Try this product free for 7 days according to the free trial terms set by the vendor.
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.m5.12xlarge Inference (Batch) Recommended | Model inference on the ml.m5.12xlarge instance type, batch mode | $0.00 |
ml.g6.12xlarge Inference (Real-Time) Recommended | Model inference on the ml.g6.12xlarge instance type, real-time mode | $12.00 |
Vendor refund policy
We do not support any refunds currently.
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.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
Initial release of document parse enhanced!
Document Parse Enhanced is an advanced mode of the existing Document Parse, significantly improving accuracy and result consistency for documents rich in visual elements such as tables, charts, diagrams, and checkboxes. It is designed to efficiently process large volumes of documents in enterprise environments—including finance, manufacturing, and the public sector—and to be readily integrated into real-world document-driven workflows.
Additional details
Inputs
- Summary
Provide input data in multipart form data View more detailed description here
To activate Enhanced Mode, you must correctly specify the mode parameter.
The mode parameter is a string value that determines the parsing mode. The following options are available: standard, enhanced, and auto. • standard: Use for text-focused documents with simple tables. • enhanced: Use for documents containing complex tables, images, charts, and other advanced visual elements. • auto: Automatically classifies each page as either standard or enhanced and processes it accordingly.
Default: "standard" Allowed values: "standard" | "enhanced" | "auto"
- Input MIME type
- multipart/form-data
https://console.upstage.ai/_next/image?url=%2Fassets%2Fimages%2Fdocs%2Finvoice.png&w=1920&q=75
BATCH INFERENCE IS NOT SUPPORTED NOW
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
mode | The mode parameter is a string value that determines the parsing mode. The following options are available: standard, enhanced, and auto.
• standard: Use for text-focused documents with simple tables.
• enhanced: Use for documents containing complex tables, images, charts, and other advanced visual elements.
• auto: Automatically classifies each page as either standard or enhanced and processes it accordingly.
Default: "standard"
Allowed values: "standard" | "enhanced" | "auto" | - | No |
Resources
Vendor resources
Support
Vendor support
Contact us for model, usage and enterprise integration inquiries.
AWS infrastructure support
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.
Similar products
nemoretriever-parse is a general purpose text-extraction model, specifically designed to handle documents. Given an image, nemoretriever-parse is able to extract formatted-text, with bounding-boxes and the corresponding semantic class. This has downstream benefits for several tasks such as increasing the availability of training-data for Large Language Models (LLMs), improving the accuracy of retriever systems, and enhancing document understanding pipelines.
IBM Granite Vision 3.3 2B is a compact multimodal model for accurate document image understanding, segmentation, and visual question answering.
Revolutionize your document processing operations with Avkalan's AI-Based Intelligent Document Processing solution. With the help of advanced machine learning algorithms, our solution facilitates the automation of extraction, analysis, and interpretation of vital information from various documents such as invoices, contracts, forms, and more. Through the elimination of human intervention and decreased errors, Avkalan enables organizations to automate processes, speed up decision-making, and enhance efficiency on a grand scale.
Customer reviews
No customer reviews yet
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.