Stained Glass Transform (SGT) by Protopia AI allows organizations to securely unlock high-value data for AI applications without compromising privacy. With lightweight, high-speed transformations, SGT strengthens data security, and expands compute options across diverse environments, while retaining model accuracy.
This SGT is specifically to be used with Nemotron-3-Super-120B
Please reach out to us at contact@protopia.ai for customized pricing before making a purchase.
Protopia AI's Stained Glass Transform (SGT) is a groundbreaking solution for organizations looking to leverage sensitive data in AI applications with robust security and flexibility. SGT transforms data into unintelligible forms, safeguarding against breaches and minimizing exposure risks without sacrificing fidelity. By enabling full data richness, SGT boosts value derived from AI models.
With its low compute overhead, SGT operates efficiently on commodity hardware, freeing up powerful GPUs for critical tasks and offering greater flexibility across on-prem, multi-tenant, and edge environments. SGT's transformation process is fast, with minimal latency, integrating seamlessly into existing AI pipelines to maximize performance and throughput.
For custom quotes and offers, please reach out at contact@protopia.ai
Highlights
Unlock AI Data Potential Securely
Access sensitive data without compromising security, enhancing AI model accuracy with high-quality inputs.
Strengthen AI Security
Convert data into unintelligible forms to eliminate exposure risks throughout AI pipelines.
Expand AI Compute Flexibility
Deploy securely on-prem, multi-tenant, and edge environments, even with minimal compute resources.
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 is based on the duration and terms of your contract with the vendor. This entitles you to a specified quantity of use for the contract duration. If you choose not to renew or replace your contract before it ends, access to these entitlements will expire.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
This listing has one pricing dimension, available through private offers only. You pay based on the number of concurrent instances of the Stained Glass Transform proxy you run. The proxy is a forward service that transforms your data before it reaches an inference server, keeping sensitive information protected. Pricing scales with how many proxy instances you deploy at once. To add capacity, you increase your instance count. Because this is a private offer, you work directly with the vendor to set contract terms and quantity for your deployment.
Top-of-mind questions for buyers
What counts as one Stained Glass Transform unit for billing?
One unit is one concurrent instance of the Stained Glass Transform proxy. The proxy is a forward service that accepts chat completion requests, transforms message contents, and forwards protected embeddings to an inference server. Each running proxy instance counts as one unit toward your total.
How does my cost change when I need to handle more traffic?
Cost scales with the number of proxy instances you run at the same time. To add capacity, you increase your concurrent instance count. Each proxy listens on a single port and processes inference requests. Running more instances at once raises your billed unit total.
Does the proxy unit include the inference server, or do I run that separately?
The proxy is a separate forward service. It sends transformed embeddings to an inference server that you point it to using environment variables. You can run that server yourself or use an AWS SageMaker endpoint. The proxy unit price covers the proxy service, not the inference server itself.
Request a private offer to receive a custom quote.
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.
Helm charts are Kubernetes YAML manifests combined into a single package that can be installed on Kubernetes clusters. The containerized application is deployed on a cluster by running a single Helm install command to install the seller-provided Helm chart.
Version release notes
v0.22.0 (2026-09-09)
Features
Bump version number for Stained Glass Proxy and Stained Glass Inference Server release (008fc7e)
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.
Stained Glass Transform (SGT) by Protopia AI allows organizations to securely unlock high-value data for AI applications without compromising privacy. With lightweight, high-speed transformations, SGT strengthens data security, and expands compute options across diverse environments, while retaining model accuracy.
This SGT is specifically to be used with Llama-3.1-8B-Instruct
Please reach out to us at contact@protopia.ai for customized pricing before making a purchase.
Run sensitive AI workloads on shared GPU infrastructure without data exposure. Stained Glass Output Protection protects tokens as they are generated by the LLM. Pairing with Stained Glass Transform (not included in this marketplace product) gives round-trip LLM protection.
NVIDIA Nemotron are open models with open weights, training data, and recipes, delivering leading efficiency and accuracy for building specialized AI agents
Llama 3.3 Nemotron Super 49B V1.5 is a significantly upgraded version of Llama 3.3 Nemotron Super 49B V1 and is a large language model (LLM) which is a derivative of Meta Llama-3.3-70B-Instruct (AKA the reference model). It is a reasoning model that is post trained for reasoning, human chat preferences, and agentic tasks, such as RAG and tool calling. The model supports a context length of 128K tokens.
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.