Sold by: Upstage
Deployed on AWS
Extract structured data from any document, regardless of type or format, using semantic understanding and user-defined schemas.
Overview
Upstage Information Extract is a schema-driven document intelligence API that transforms unstructured content into structured data. It applies semantic understanding across any document type or format to reliably capture the information you define.
User-Defined Schema Extraction: Define exactly the fields you need, from simple key-values to complex nested structures. Unlike fixed and predefined key extraction, this flexible engine adapts to any document structure.
Semantic Understanding: Going beyond position or template-based extraction, it extracts data based on a deep semantic understanding of both the document context and the user-defined schema.
Designed for Reliable Automation: We prioritize reliability and traceability, allowing users to verify reference locations and confidence scores for seamless human-in-the-loop workflows.
Highlights
- Schema-Driven Extraction: Define what to extract using flexible schemas. Works across any document type or layout, capturing structured data exactly as specified.
- Semantic, Inference-Based Extraction: Analyzes document meaning to extract data beyond explicit text. Captures fields even when values are implied, unlabeled, or expressed in varied ways.
- Key Tasks: Key-Value Extraction - Table to Structured JSON - Nested & Hierarchical Data Extraction - Multi-Document Consistency - Field-Level Location Tracking - Confidence Scoring - Schema Generation
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.g7e.4xlarge Inference (Real-Time) Recommended | Model inference on the ml.g7e.4xlarge instance type, real-time mode | $20.00 |
ml.m5.12xlarge Inference (Batch) Recommended | Model inference on the ml.m5.12xlarge instance type, batch mode | $20.00 |
ml.g7e.2xlarge Inference (Real-Time) | Model inference on the ml.g7e.2xlarge instance type, real-time mode | $20.00 |
ml.g7e.8xlarge Inference (Real-Time) | Model inference on the ml.g7e.8xlarge instance type, real-time mode | $20.00 |
ml.g7e.12xlarge Inference (Real-Time) | Model inference on the ml.g7e.12xlarge instance type, real-time mode | $20.00 |
ml.g7e.24xlarge Inference (Real-Time) | Model inference on the ml.g7e.24xlarge instance type, real-time mode | $25.00 |
ml.g7e.48xlarge Inference (Real-Time) | Model inference on the ml.g7e.48xlarge instance type, real-time mode | $30.00 |
Dimensions summary
You pay by the host hour based on the AWS instance type you run. Six real-time inference options use the ml.g7e family, sized from 2xlarge up to 48xlarge. As you move to a larger instance, you get more compute for higher-throughput document extraction. One batch inference option runs on the ml.m5.12xlarge instance for jobs processed in bulk rather than in real time. You choose the mode and instance size that fit your workload, and billing accrues only for the hours each instance stays running.
Top-of-mind questions for buyers
Billing accrues per host hour while an instance stays running. A fully stopped instance stops accruing software host charges. Underlying AWS storage or other resources tied to a stopped instance may still incur separate AWS fees, but the inference charge meters running time only.
Both meter per host hour with no upfront commitment. The real-time ml.g7e options keep an instance running to serve requests as they arrive. The ml.m5.12xlarge batch option processes documents in bulk jobs. Real-time suits live extraction; batch suits large volumes processed together.
Information Extract pulls structured key-value data from documents like invoices, claims, and contracts. It processes scanned images, PDFs, Office files, rotated pages, and documents spanning hundreds of pages. Larger instance sizes give you more compute for higher-throughput extraction across these formats.
www.upstage.ai
Helpful?
Vendor refund policy
Contact us for refund inquiries. https://www.upstage.ai/contact-us?utm_source=marketplace
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
Minor update: Introduced hierarchical classification support for document classify
Additional details
Inputs
- Summary
Provide input data in JSON request body. The api field (SageMaker-specific) selects one of three modes:
- information-extraction — Request body
- schema-generation — Request body
- document-classification — Request body
Apart from the api field, each mode's request body matches the linked spec.
- Input MIME type
- application/json
https://console.upstage.ai/assets/images/docs/bank_statement.png
BATCH INFERENCE IS NOT SUPPORTED NOW
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
Financials Extractor helps you to identify financial Information of an organization using its annual report.
The Wipro HOLMES™ Controller Extractor helps to identify controllers (CEO, CTO, Chairman etc.) of an organization using its annual report
YomiToku is a proprietary document analysis engine specialized for Japanese. It integrates AI OCR plus layout and table parsing models, accurately structuring vertical text, multi column documents, and complex business forms. It supports a wide range of use cases, including generating data for RAG / search, creating searchable PDFs, and extracting information from table data.
We provide yomitoku-client as a client SDK to help you use this product more conveniently.For more details, please refer to the link below:
https://github.com/MLism-Inc/yomitoku-client
For long-term or large-scale use, this product is also available through private offers.Please contact our support team for pricing information.
Extract structured information or convert messy documents into clean HTML - all with a single API. No fine-tuning, , no re-training, just results.
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.