Overview
CUBIG LLM Capsule is an AI privacy gateway for teams that need to use external LLMs or AI agents but cannot send raw customer or sensitive enterprise data outside their environment. Before prompts leave the organization, LLM Capsule detects regulated fields and applies masking, pseudonymization, or tokenization inline; only transformed content is sent to approved external models. After the response returns, LLM Capsule automatically restores authorized original values through detokenization, so downstream workflows receive usable answers without any manual re-mapping. This round-trip protection supports safer external AI adoption in environments shaped by privacy, credit-data, and sector-specific cloud controls.
Highlights
- Detect and mask personal, financial, and regulated data before prompts leave the environment
- Preserve model context with pseudonymization and tokenization instead of sending raw identifiers to external models
- Restore authorized values after response return with policy controls and audit logs for regulated external AI use
Details
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
Pricing
Dimension | Description | Cost/month |
|---|---|---|
License | LLM Capsule License | $4,000.00 |
Vendor refund policy
test refund policy
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
unit delivery option
- Amazon ECS
Container image
Containers are lightweight, portable execution environments that wrap server application software in a filesystem that includes everything it needs to run. Container applications run on supported container runtimes and orchestration services, such as Amazon Elastic Container Service (Amazon ECS) or Amazon Elastic Kubernetes Service (Amazon EKS). Both eliminate the need for you to install and operate your own container orchestration software by managing and scheduling containers on a scalable cluster of virtual machines.
Version release notes
Version 1.0.3 - Security & Compliance Update
- Container runs as non-root user (UID: 1000) for enhanced security
- Added health check endpoint (/health)
- Removed unnecessary dependencies
- Optimized container image structure
- Updated documentation for external dependencies
Additional details
Usage instructions
Usage Instructions
- Prerequisites
- Docker runtime environment (Amazon ECS, EKS, etc.)
- No external database required
-
Environment Variables Refer to product documentation for required environment variables.
-
Run Container docker run -d -p 8080:8080 <image-uri>
-
Verify Health Check curl http://localhost:8080/health Expected response: {"status":"healthy"} or similar
-
External Dependencies
- No external database required
- No external paid APIs required
- All AI processing is performed locally within the container
-
Included Packages (from PyPI) fastapi, uvicorn, torch, transformers, huggingface-hub, pandas, numpy, cryptography, pydantic All packages use permissive licenses (MIT, BSD, Apache-2.0) for commercial use.
-
Security
- Container runs as non-root user (UID: 1000)
- Health check endpoint: /health
- Exposed port: 8080
Support
Vendor support
Please reach us at contact@cubig.ai for any assistance or questions.
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.