Sold by: Upstage
Deployed on AWS
Extract all text from any document
Overview
Upstage Document OCR (Optical Character Recognition) is designed to efficiently detect and recognize text from a wide range of document images, ensuring high accuracy and versatility across various languages and image qualities.
Highlights
- ### Key Features - **Word-Level Coordinate/Transcription Results:** Provides word-level bounding box and transcription for easy text processing. - **Robustness on Rotated Documents:** Detects and corrects text orientation in rotated documents. - **Multilingual Text Detection:** Recognizes texts in multiple languages.(English, Chinese, Japanese, and Korean) - **Confidence Scores:** Outputs word-level confidence scores to assess reliability of extracted text for further verification.
- ### Key Applications - **Automated Data Entry:** Converts printed or handwritten documents into digital text, streamlining data entry and reducing manual effort. - **Archival and Digitization:** Digitizes documents, books, and records, preserving information and making it searchable and accessible. - **Multilingual Document Processing:** Handles documents in English and CJK (Chinese, Japanese, Korean), enabling effective international document processing.
- ### Key Tasks - Text Extraction - Document Digitization - Multilingual Document Handling - Automated Data Entry - Information Retrieval
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.xlarge Inference (Real-Time) Recommended | Model inference on the ml.g6.xlarge instance type, real-time mode | $1.50 |
ml.g6.xlarge Inference (Batch) Recommended | Model inference on the ml.g6.xlarge instance type, batch mode | $1.50 |
ml.m5.12xlarge Inference (Batch) | Model inference on the ml.m5.12xlarge instance type, batch mode | $0.00 |
ml.p3.2xlarge Inference (Real-Time) | Model inference on the ml.p3.2xlarge instance type, real-time mode | $1.50 |
ml.g6.2xlarge Inference (Real-Time) | Model inference on the ml.g6.2xlarge instance type, real-time mode | $1.50 |
ml.g5.xlarge Inference (Real-Time) | Model inference on the ml.g5.xlarge instance type, real-time mode | $1.50 |
ml.g5.2xlarge Inference (Real-Time) | Model inference on the ml.g5.2xlarge instance type, real-time mode | $1.50 |
ml.g4dn.xlarge Inference (Real-Time) | Model inference on the ml.g4dn.xlarge instance type, real-time mode | $1.50 |
ml.g5.xlarge Inference (Batch) | Model inference on the ml.g5.xlarge instance type, batch mode | $1.50 |
ml.g5.2xlarge Inference (Batch) | Model inference on the ml.g5.2xlarge instance type, batch mode | $1.50 |
Dimensions summary
You pay by the hour for the compute instance that runs the Document OCR model. Pricing is organized by two choices. First, you pick an instance type, ranging from GPU-based options to a CPU-based ml.m5.12xlarge. Second, you pick an inference mode: real-time for immediate responses or batch for processing groups of documents. Real-time modes run on GPU instances, while batch modes cover both the CPU instance and several GPU instances. Your cost scales with which instance size you choose and how many host hours you run.
Top-of-mind questions for buyers
One host hour is one hour that your chosen instance runs the Document OCR model. Charges accrue only while the instance is running. When you stop the instance, software host-hour charges stop. Underlying AWS storage or other resource fees may still apply separately.
Both meter host hours the same way, but they suit different work. Real-time mode keeps an instance running to answer requests as they arrive, so you pay for uptime. Batch mode processes groups of documents together, so you run the instance only for the length of each job.
Yes. Each file can be up to 50MB and 100 pages, with a page pixel cap of 200,000,000. Supported formats include JPEG, PNG, BMP, PDF, TIFF, HEIC, and common office documents. These limits apply per file regardless of which instance or mode you choose.
console.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
- Improved Character detection / recognition
- Improved GPU memory usage
- Support for batch transform
Additional details
Inputs
- Summary
Provide input data in multipart form data View more detailed description here
- 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%2Fhello.png&w=1920&q=75
https://console.upstage.ai/_next/image?url=%2Fassets%2Fimages%2Fdocs%2Fhello.png&w=1920&q=75
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
Transform complex documents into structured, schema-compliant JSON using the top-ranked self-hosted OCR model. Built for enterprise document automation, JSL Vision OCR Structured LLM extracts data from PDFs, forms, tables, and scanned documents while keeping sensitive information within your AWS environment.
This product has charges associated with it for hardening, security configuration, and support.
Paperless-ngx is an open-source document management system that scans, OCRs, and archives your documents. This Lynxroute build is security baked in: Nginx TLS reverse proxy, admin credentials generated at first boot, PostgreSQL and Redis bound to localhost only, and CIS Level 1 hardened Ubuntu 24.04 LTS base.
GPL-3.0 license - fully auditable, no vendor lock-in.
Scalable OCR processing service delivered via API, designed for high-volume document and image workflows. Includes optional rasterization to convert PDFs into OCR-ready image formats. Ideal for organizations seeking efficient, pay-per-use document text extraction without data retention. Compatible with cloud-native applications and easily integrated into existing platforms.
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.