PaddleOCR reads English text from PNG and JPEG images on CPU and returns each word with a confidence score and bounding box as JSON. This Ubuntu 24.04 AMI includes a private HTTPS upload page and API with a per-instance password, so teams can digitize images without sending them to an external OCR service.
PaddleOCR is an open source optical character recognition toolkit. This AMI is for developers and operations teams who need to extract English text from screenshots, photos of documents or forms and keep the images inside their own AWS account.
What you get: PaddleOCR 3.7.0 on CPU behind HTTPS port 8443 with a password created on first boot. A browser upload page draws the detected text boxes on your image, the API returns JSON with each word, a confidence score and a four-corner box (OpenAPI description at /openapi.json), and the command sushi-paddleocr-api ocr page.png prints the text on the instance. One PNG or JPEG is processed at a time. PDF files, web addresses, GPU execution and languages other than English are not included.
Getting started: launch t3.large with at least 32 GiB of encrypted gp3 storage and IMDSv2, keep inbound application ports closed and connect with Session Manager. Run sudo -iu ubuntu bash /opt/sushi/docs/demo.sh, forward port 8443 and upload an image. Back up stored jobs before replacing an instance.
This is a repackaged open source software product wherein additional charges apply for independent AWS packaging, setup documentation and maintenance by Software Sushi. PaddlePaddle publishes PaddleOCR under the Apache-2.0 license. Software Sushi is independent of the upstream project and does not claim upstream or AWS endorsement. EC2, EBS and data transfer are billed separately from software charges.
Highlights
Extract English text from PNG and JPEG images on CPU.
JSON output with each word, a confidence score and a bounding box; a browser page shows the boxes on your image.
Private HTTPS on this instance with a per-instance password. Images stay in your AWS account.
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.
Try this product free for 5 days according to the free trial terms set by the vendor. Usage-based pricing is in effect for usage beyond the free trial terms. Your free trial gets automatically converted to a paid subscription when the trial ends, but may be canceled any time before that.
You pay one usage-based rate for this software, billed per hour on a t3.large Amazon EC2 instance. There is just one pricing dimension, so there are no tiers or sizes to choose between. The software charge accrues for each hour the instance runs. This reads English text from PNG and JPEG images on CPU and returns words, confidence, and word boxes as JSON. AWS infrastructure costs such as EC2, storage, and data transfer are billed separately. You launch the image in your own AWS account and manage the instance yourself.
Top-of-mind questions for buyers
What do I get on the t3.large instance this product runs on?
You get the PaddleOCR software preconfigured on a t3.large Amazon EC2 instance running on CPU. It reads English text from PNG and JPEG images and returns words, confidence scores, and word boxes as JSON. You add any credentials after launch, and each instance generates its own secrets on first boot.
Am I charged when the instance is stopped?
The software charge accrues per hour while the t3.large instance runs. A fully stopped instance does not accrue software charges. However, stopped instances may still incur AWS storage fees for attached volumes. The software meters running time only. You control when the instance starts and stops in your own AWS account.
What costs are separate from the hourly software charge?
AWS infrastructure is billed separately from the software charge. This includes EC2 compute, EBS storage, networking, and data transfer. The hourly rate covers the PaddleOCR software only. Because the tool runs on CPU, no GPU or external model-provider account is required for the recognition work itself.
softwaresushi.com
Helpful?
Vendor refund policy
We offer a full refund of software charges for the first 48 hours billing starts if the product does not perform as described. To request a refund, email info@softwaresushi.com with your EC2 instance ID and a description of the issue. AWS infrastructure costs (EC2, EBS, data transfer) and any third-party service charges are not eligible for refund by us.
How can we make this page better?
Tell us how we can improve this page, or report an issue with this product.
Give us feedbackReport a problem with this product or seller
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.
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
PaddleOCR 3.7.0 on Ubuntu 24.04 for t3.large. Rebuilt host and runtime with no matches for AWS Marketplace CVE-2026-111497. Retains the local HTTPS upload page, text boxes, OpenAPI description, sushi-paddleocr-api command and first-run timeout improvements.
Additional details
Usage instructions
Launch t3.large with at least 32 GiB encrypted gp3 root storage and IMDSv2; keep inbound application ports closed. 2. Connect with AWS Systems Manager Session Manager (no key pair or inbound rule needed); you land as ssm-user. 3. Wait for cloud-init and run sudo -iu ubuntu bash /opt/sushi/docs/demo.sh. 4. Forward port 8443 with Session Manager, open local port 8443 over HTTPS in your browser and log in with the username and password from ~/.config/sushi/paddleocr/access.json; upload a PNG or JPEG to see the text and boxes. On the instance, sushi-paddleocr-api ocr page.png prints the text. The guide is in the guide at /opt/sushi/docs/README.md on the instance. 5. Back up stored jobs before replacing the instance. EC2, EBS, and data transfer are billed separately from software.
Software Sushi provides installation and configuration guidance for this image. Contact info@softwaresushi.com with your product version and reproduction steps; never send keys or private configuration. Guaranteed response times require a separate agreement. This offer does not include upstream project 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.
Generate natural English speech from text with Chatterbox Nano on CPU, in the voice of a short sample you provide. This Ubuntu 24.04 AMI runs a private, token-protected speech service in your own AWS account, so you can create narration and voice prompts without sending text or voice data to a third-party service.
Transcribe English and Spanish audio on CPU with faster-whisper and a pinned multilingual small model. This Ubuntu 24.04 AMI returns text with segment and word timestamps through a private HTTPS API with per-instance TLS. Audio stays on the instance, with no model API account or GPU needed.
Presidio finds and redacts personal data such as names, emails, phone numbers and IDs in text. This Ubuntu 24.04 AMI runs Presidio with pinned English and Spanish spaCy models behind a private HTTPS API with per-instance TLS, so teams can clean data before it reaches logs, analytics or LLMs, with no external API.
Docling converts PDF and DOCX files into clean Markdown and structured JSON for search, RAG pipelines and data extraction. This Ubuntu 24.04 AMI runs Docling on CPU behind a private HTTPS API with per-instance TLS. Processing stays on the instance, with no model API key and no remote services.
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.