Sold by: Upstage
Deployed on AWS
Extract tables and figures from any document
Overview
Upstage Document Parse is a powerful API designed to automatically convert any document to HTML. It detects layout elements such as paragraphs, tables, images, equations, charts and more to determine the structure of the document. The API then serializes the elements according to reading order, and finally converts the document into HTML.
Highlights
- ### Key Features **Text Recognition** detects text via OCR or PDF parsing, excelling in English and CJK documents, including digital-born PDFs. **Layout Element Detection (LED)** identifies paragraphs, figures, tables, and captions, arranging them in human reading order - great for complex layouts. **Table Structure Recognition (TSR)** converts complex tables to HTML, handling merged cells and hidden gridlines.
- ### Key Applications The Upstage Document Parse model enhances LLM-based document processing and information retrieval by preserving contextual information better than traditional OCR. It is valuable for scenarios where LLMs process documents, integrating RAG with Layout Analysis via embedding techniques. It excels in information extraction and recognizing document structures across various templates, making it ideal for handling the same type of documents in different formats.
- ### Key Tasks - Document OCR - Document Parsing - Layout Analysis - Information Extraction - Layout Element Detection - Table Structure Recognition
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
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.g6.2xlarge Inference (Real-Time) Recommended | Model inference on the ml.g6.2xlarge instance type, real-time mode | $10.00 |
ml.g5.2xlarge Inference (Batch) Recommended | Model inference on the ml.g5.2xlarge instance type, batch mode | $10.00 |
ml.m5.12xlarge Inference (Batch) | Model inference on the ml.m5.12xlarge instance type, batch mode | $10.00 |
ml.p3.2xlarge Inference (Real-Time) | Model inference on the ml.p3.2xlarge instance type, real-time mode | $10.00 |
ml.g5.xlarge Inference (Real-Time) | Model inference on the ml.g5.xlarge instance type, real-time mode | $10.00 |
ml.g5.2xlarge Inference (Real-Time) | Model inference on the ml.g5.2xlarge instance type, real-time mode | $10.00 |
ml.g4dn.xlarge Inference (Real-Time) | Model inference on the ml.g4dn.xlarge instance type, real-time mode | $10.00 |
ml.g6.xlarge Inference (Real-Time) | Model inference on the ml.g6.xlarge instance type, real-time mode | $10.00 |
ml.g5.xlarge Inference (Batch) | Model inference on the ml.g5.xlarge instance type, batch mode | $10.00 |
ml.g6.xlarge Inference (Batch) | Model inference on the ml.g6.xlarge instance type, batch mode | $10.00 |
Dimensions summary
You pay by the hour for each host running Document Parse, based on the AWS instance type you choose. Pricing scales with instance size and family. Larger instances within a family carry higher hourly rates. Each instance also comes in two modes: real-time, which serves live requests, and batch, which processes documents in bulk jobs. You pick the instance type and mode that fit your workload, then pay only for the hours each host runs. No upfront commitment applies to these hourly rates.
Top-of-mind questions for buyers
Real-time mode serves live requests one document at a time, suited for interactive or on-demand parsing. Batch mode processes documents in bulk jobs, suited for large volumes handled together. Each mode bills per host-hour on the instance type you select. You pick the mode that matches your workload pattern.
A host-hour is one running instance billed for each hour it stays active, regardless of how many documents it parses. Charges accrue while the host runs, even during idle periods. Stopping the instance ends software metering, though underlying AWS infrastructure fees may still apply separately.
Hourly rates do not change with document count. You pay per host-hour, not per page. Document Parse processes about 0.6 seconds per page on average, so a running host can parse many documents within one billed hour. Faster throughput lets each host-hour cover more pages.
www.upstage.ai
Helpful?
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
🚀 Updates
- Wider OCR coverage, including superscript/subscript digits and common math symbols.
- Improved text recognition accuracy.
- Improved layout detection for images in digital-born documents.
- Fixed an issue which happened on rare occasions where text not present in the image appeared in the output.
Additional details
Inputs
- Summary
Provide input data in multipart form data. View more detailed description here - https://console.upstage.ai/api/document-digitization/document-parsing#request-body
- Input MIME type
- multipart/form-data, application/pdf, image/jpeg, image/png, image/tiff, image/bmp, application/octet-stream, application/vnd.openxmlformats-officedocument.wordprocessingml.document, application/vnd.openxmlformats-officedocument.presentationml.presentation, application/vnd.openxmlformats-officedocument.spreadsheetml.sheet, application/vnd.hancom.hwpx, application/x-hwp
https://console.upstage.ai/_next/image?url=%2Fassets%2Fimages%2Fdocs%2Finvoice.png&w=1920&q=75
S3 path is required.
s3://test-assets/document-parse/input/test_image.jpg
Resources
Vendor resources
Support
Vendor support
Contact us for model 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
Parse PDFs, images, and scans into LLM-ready HTML. VLM-powered analysis for complex tables & charts.
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.
Turn documents into AI-ready data. Build accurate search, RAG, and agentic workflows more efficiently.
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.