Sold by: MLism Inc.
Deployed on AWS
YomiToku is a proprietary document analysis engine specialized for Japanese. This Lite edition runs a lightweight recognition model for higher throughput and lower cost per page, with slightly lower accuracy than the standard edition. It is a good fit for high volume batch processing and cost sensitive workloads. 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.
Overview
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.
This is the Lite edition of YomiToku. It runs a lightweight recognition model that delivers significantly higher throughput and a lower cost per page than the standard edition, with slightly lower recognition accuracy. It is designed for high volume batch processing and cost sensitive workloads, such as digitizing large document archives, building RAG / search indexes from bulk data, and continuous ingestion pipelines. Layout analysis, table structure recognition, and the response format are identical to the standard edition, so you can move between the two editions without changing your integration. If your workload prioritizes maximum recognition accuracy over throughput, we recommend the standard edition instead.
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.
Highlights
- Each model is specifically trained for Japanese document images, supporting the recognition of over 7,000 Japanese characters, including vertical text and other layout structures unique to Japanese documents. (It also supports English documents.)
- Equipped with four AI models trained on Japanese datasets: text detection, text recognition, layout analysis, and table structure recognition. All models are independently trained and optimized for Japanese documents, delivering high-precision inference.
- By leveraging layout analysis, table structure parsing, and reading order estimation, it extracts information while preserving the semantic structure of the document layout.
Details
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 (Batch) Recommended | Model inference on the ml.g6.xlarge instance type, batch mode | $10.00 |
ml.g4dn.xlarge Inference (Real-Time) Recommended | Model inference on the ml.g4dn.xlarge instance type, real-time mode | $10.00 |
ml.g4dn.xlarge Inference (Batch) | Model inference on the ml.g4dn.xlarge instance type, batch mode | $10.00 |
ml.g5.xlarge Inference (Batch) | Model inference on the ml.g5.xlarge instance type, batch mode | $10.00 |
ml.c7i.xlarge Inference (Batch) | Model inference on the ml.c7i.xlarge instance type, batch mode | $10.00 |
ml.c7i.2xlarge Inference (Batch) | Model inference on the ml.c7i.2xlarge instance type, batch mode | $10.00 |
ml.g5.xlarge Inference (Real-Time) | Model inference on the ml.g5.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.c7i.xlarge Inference (Real-Time) | Model inference on the ml.c7i.xlarge instance type, real-time mode | $10.00 |
ml.c7i.2xlarge Inference (Real-Time) | Model inference on the ml.c7i.2xlarge instance type, real-time mode | $10.00 |
Dimensions summary
You pay by the hour for the compute instance that runs document analysis in your own AWS account. The ten dimensions pair five instance types with two processing modes. Three instance types use GPU acceleration, and two use general-purpose CPU compute. Each instance runs in either batch mode, for processing large volumes of documents, or real-time mode, for on-demand requests. Pick the instance size that fits your workload and the mode that matches how you send documents. Charges accrue per host hour that the instance runs. This billing covers software use; the AWS instance is billed separately.
Top-of-mind questions for buyers
One host hour is one hour that a single deployed SageMaker endpoint instance runs. The listing meters this software use per running hour. The underlying AWS compute charge for that instance is billed separately by AWS. Both appear on your AWS invoice.
Both modes bill per host hour on the same instance types. Real-time mode keeps an endpoint running to answer on-demand requests, so hours accrue while it stays up. Batch mode processes large document sets in scheduled runs, so hours accrue during those jobs. Choose the mode matching how you send documents.
Charges accrue per host hour that the instance runs. A real-time endpoint left running keeps accruing hours even without active requests. If you shut the endpoint down, software host-hour charges stop. Underlying AWS storage or other resources may still bill separately.
www.mlism.com
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
Initial release of the Lite edition of YomiToku-Pro - Document Analyzer.
Additional details
Inputs
- Summary
Supported Content Types:
- application/pdf - PDF documents (multi-page supported)
- image/jpeg - JPEG images
- image/png - PNG images
- image/tiff - TIFF images
Request Body:
Send the binary file data directly in the request body with appropriate Content-Type header.
Example Usage:
aws sagemaker-runtime invoke-endpoint --endpoint-name ${ENDPOINT_NAME} --content-type "application/pdf" --body fileb://demo/sample.pdf --region ${AWS_REGION} output.json
Sample Image Source:
The sample images used in this documentation are from 「広報誌 令和 6 年 11 月号」 published by 総務省.
- Limitations for input type
- ## Input MIME type application/pdf, image/jpeg, image/png, image/tiff
- Input MIME type
- application/pdf, image/jpeg, image/png, image/tiff
https://mlism-marketplace-documents.s3.ap-northeast-1.amazonaws.com/samples/gallery1.jpg
https://mlism-marketplace-documents.s3.ap-northeast-1.amazonaws.com/samples/gallery1.jpg
Support
Vendor support
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
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.
dotData Cloud Insight Lite offers a fully-managed cloud service with comprehensive support, infrastructure, and management. Tailored for small and medium enterprises (SMEs), it provides the full capabilities of dotData Insight, the revolutionary analytics platform powered by Generative AI and dotData’s AI. SME clients can extract all key signals driving business growth without requiring significant manpower or advanced analytics expertise.
Text embedding model optimized for general-purpose retrieval quality, latency, and cost for AI applications. 32K context length.
Lasius Lite is an AI agent platform for IT support and help desk automation. Deploy multi provider LLM agents that triage and resolve tickets, search your knowledge base, and automate workflows with streaming chat, team workspaces, and a REST API.
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.