Sold by: Reducto
Deployed on AWS
Deploy Reducto r-1 mini on Amazon SageMaker in your AWS account. Turn complex document pages into structured data that preserves content, layout, and meaning for AI and business workflows.
Overview
Reducto builds AI infrastructure for enterprise documents. r-1 mini is its unified parsing model, built to help developers turn complex document pages into structured content their applications can use. It reads text, tables, layout, and formatting together, preserving reading order and the relationships that carry meaning across financial statements, contracts, forms, and scans. Use the output as a foundation for RAG, enterprise search, AI agents, and document-driven business workflows.
Deploy r-1 mini through AWS Marketplace as an Amazon SageMaker endpoint on compute in your own AWS account. Your application sends rendered document pages to the endpoint and receives machine-readable parsed content for downstream processing. This brings document understanding into your existing systems while running model inference in your AWS environment.
Highlights
- Document understanding beyond text recognition: r-1 mini reads text, tables, layout, and formatting together, preserving the structure and meaning that simple OCR can lose.
- Deployed in your AWS account: Run r-1 mini as an Amazon SageMaker endpoint on your AWS compute and connect it to the document applications you already use.
- Built for varied documents and workflows: Parse financial statements, contracts, forms, and scans into machine-readable content for RAG, search, AI agents, and downstream business processes.
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 |
|---|---|---|
ml.g6e.2xlarge Inference (Batch) Recommended | Model inference on the ml.g6e.2xlarge instance type, batch mode | $100.00/host/hour |
inference.count.m.i.c Inference Pricing | inference.count.m.i.c Inference Pricing | $0.01/request |
Vendor refund policy
Reducto bills real-time use per successful request and batch transform use per instance-hour. Requests that return an error are not billed. To request a refund, email support@reducto.ai within 30 days of the charge with your AWS account ID and the charge details. Reducto reviews each request and answers within 5 business days. AWS infrastructure charges are billed by AWS and are not refunded by Reducto.
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
First release of Reducto r-1 mini on Amazon SageMaker. r-1 mini parses one document page per request. It returns the blocks of the page in reading order, and each block has a type, a bounding box, and the content. A table is HTML. The model runs on real-time endpoints and on batch transform jobs on ml.g6e.2xlarge.
Additional details
Inputs
- Summary
r-1 mini takes one document page per request: a PNG or JPEG image in a JSON body of at most 6 MB. Send the page-parse body {"image_b64": ...} or an OpenAI chat-completions body with one image_url part. max_pixels (1 to 6,291,456, default 3,145,728) limits the image size: r-1 mini scales a larger image down. A body over 6 MB is refused. A request that fails validation, for example a data: URL that is not a PNG or JPEG, returns HTTP 422 with {"detail": "invalid request"}. Image bytes that are not a readable PNG or JPEG, or an image with more than 25,165,824 pixels, return HTTP 415 with {"detail": "invalid input"}. In real-time, SageMaker shows the 415 and the 422 as a 424 ModelError with the status in OriginalStatusCode.
- Limitations for input type
- PNG or JPEG only. One page per request. The JSON body is at most 6 MB. A real-time request must finish within 55 seconds.
- Input MIME type
- application/json
https://github.com/reductoai/reducto-cookbook/blob/main/r-1-mini/samples/invoice.request.json
https://github.com/reductoai/reducto-cookbook/blob/main/r-1-mini/samples/invoice.request.json
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
image_b64 | String. The base64 PNG or JPEG of one document page (page-parse body). | The full JSON body is at most 6 MB. | Yes |
max_pixels | Integer. r-1 mini scales a larger image down to this many pixels before it reads the page. Default 3,145,728. | 1 to 6,291,456 | No |
Support
Vendor support
Technical support via support@reducto.ai for deployment, integration, and troubleshooting; self-service documentation at https://docs.reducto.ai . Any dedicated support or response-time commitments should follow the buyer's agreement.
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
Reducto provides high-quality document ingestion for AI teams by accurately parsing complex documents like PDFs, Excel spreadsheets, and PowerPoint slides. It combines computer vision and new vision-language models for precise, LLM-ready data extraction.
Reducto provides high-quality document ingestion for AI teams by accurately parsing complex documents like PDFs, Excel spreadsheets, and PowerPoint slides. It combines computer vision and new vision-language models for precise, LLM-ready data extraction.
The professional services solution that allows you to modernize legacy systems starting from 3 variables:
Number of Tables
Number of Store procedures
Size in GB of the DB
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.