Overview

Product video
Run Gradio 6.30.0 with an authenticated web interface and queue API for a local sentiment classifier. The original starter trains a small multinomial Naive Bayes model on twelve synthetic English phrases using Python standard-library code. Each prediction returns a saved ID, label and probabilities. The installed reader checks the JSON against SQLite and independently recomputes the probabilities from the original training bytes. This is a teaching example, not a pretrained language model or a consequential decision system.
Automatic first boot creates instance-specific credentials and database identity. Gradio runs as ubuntu and listens only on loopback port 7860. Connect through a Session Manager or SSH tunnel and sign in with the launch-created account. Public sharing and telemetry are disabled. No model download, provider account, API key or paid model call is required for the supplied starter.
Results and launch identity persist across service restarts and reboots. Back up the SQLite state, access identity and exported results together; replacing an AMI does not migrate a running instance. Original wheels, source archives and component notices are delivered with the image. Gradio uses Apache-2.0; included components retain their own licenses.
This is a repackaged open source software product wherein additional charges apply for independent AMI packaging, maintenance and setup documentation. Software Sushi is an independent packager and claims no upstream or AWS endorsement.
Software costs USD 0.03 per running instance-hour. EC2, EBS and data transfer are billed separately. The supplied local starter has no model-provider usage charge. Installation support: info@softwaresushi.com .
Highlights
- Authenticated Gradio UI and queue API for a local synthetic sentiment model, without provider keys or model downloads.
- SQLite prediction IDs, JSON results and an independent reader that recomputes probabilities from original training data.
- Launch-created credentials, nonroot automatic services and loopback access through a Session Manager or SSH tunnel.
Details
Features and programs
Financing for AWS Marketplace purchases
Pricing
Free trial
Dimension | Cost/hour |
|---|---|
t3.large Recommended | $0.03 |
Dimensions summary
Top-of-mind questions for buyers
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) are not eligible for refund by us.
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
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
Use an authenticated Gradio interface for local sentiment predictions, persistent SQLite results and independent readback on Ubuntu 24.04. Launch t3.large with at least 8 GiB RAM and 32 GiB encrypted gp3 root storage. Require IMDSv2.
Additional details
Usage instructions
Launch t3.large with at least 8 GiB RAM and 32 GiB encrypted gp3 root storage. Require IMDSv2. Wait for automatic first boot, then connect using Session Manager and switch to ubuntu with sudo -iu ubuntu. Forward remote loopback port 7860 using AWS-StartPortForwardingSession and open http://127.0.0.1:7860 locally. Read /home/ubuntu/.config/sushi-gradio/access.json only in an unrecorded shell and sign in. Run bash /opt/sushi/docs/demo.sh, or use sushi-gradio predict and sushi-gradio read with a new output path. Predictions persist in /var/lib/gradio/predictions.sqlite3; back it up with the access file and ~/gradio-results. Do not delete identity files to reset setup. Read /opt/sushi/docs/README.md. No model-provider account or usage charge is required by this local starter. Software costs USD 0.03 per running instance-hour. EC2, EBS and data transfer are billed separately. The supplied local starter has no model-provider usage charge. Getting started: https://softwaresushi-marketplace-branding-public.s3.us-east-1.amazonaws.com/docs/gradio/getting-started-7905cc53ca404759b44dcbe60880d0d2930149e98a119cb421efc82a896271ec.html
Resources
Vendor resources
Support
Vendor support
Software Sushi provides AMI packaging and setup guidance. Contact info@softwaresushi.com for installation questions. Support coverage requires 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.