Sold by: GJ Sev
Deployed on AWS
SWN AI Gateway is an enterprise-grade multi-LLM orchestration platform that provides a unified OpenAI-compatible API for routing requests across OpenAI, Anthropic, Gemini, DeepSeek, local models, and custom AI providers with built-in observability, failover, caching, and security controls.
Overview
SWN AI Gateway is a deployable enterprise AI infrastructure platform designed to simplify and standardize access to multiple large language model providers through a single OpenAI-compatible API interface.
The platform enables organizations to centrally manage AI traffic across OpenAI, Anthropic Claude, Google Gemini, DeepSeek, self-hosted models, and custom providers while maintaining full infrastructure control inside their AWS environment.
Built for enterprises and AI-native engineering teams, SWN AI Gateway provides intelligent routing, failover handling, observability, rate limiting, structured outputs, streaming support, API normalization, prompt caching, logging, and AI firewall capabilities.
The solution can be deployed within Amazon EKS, ECS, EC2, Kubernetes environments, or private VPC infrastructures using containerized deployment workflows.
Key capabilities include:
Unified OpenAI-compatible API endpoint Multi-provider LLM orchestration Smart model routing and fallback Prompt caching and cost optimization Enterprise observability and logging Streaming and structured output support AI security and policy enforcement Vendor lock-in reduction Self-hosted enterprise deployment Kubernetes and container-native architecture
SWN AI Gateway is ideal for enterprises building scalable AI platforms, internal copilots, AI applications, workflow automation systems, and multi-model inference infrastructures.
Highlights
- Unified OpenAI-compatible API for OpenAI, Claude, Gemini, DeepSeek, and self-hosted models.
- Enterprise-grade observability, logging, routing, failover, and AI traffic management.
- Deploy securely inside your AWS infrastructure using Kubernetes, ECS, or container-based workflows.
Details
Sold by
Categories
Delivery method
Supported services
Delivery option
Container Deployment
Latest version
Operating system
Linux
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 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.
Dimension | Description | Cost/month |
|---|---|---|
Starter Plan | Ideal for startups and small engineering teams deploying a unified AI gateway with multi-provider routing and observability capabilities. | $50.00 |
Business Plan | Designed for growing organizations requiring advanced routing, failover handling, enterprise observability, and production AI infrastructure management. | $80.00 |
Enterprise Plan | Enterprise-grade deployment with large-scale orchestration, advanced governance, private infrastructure deployment, and premium support. | $120.00 |
Vendor refund policy
Refund requests must be submitted within 14 days of purchase. Refunds may be granted in cases where the product is non-functional or materially fails to operate as described. Refund eligibility is determined at the sole discretion of SWN LLC. For refund inquiries, contact support@swnllc.io .
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
Container Deployment
Supported services: Learn more
- Amazon ECS
- Amazon ECS Anywhere
- Amazon EKS
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
Aegis Gateway v1.0.2 Streaming reliability fix
Bug fixes Streaming chat completions (POST /v1/chat/completions with "stream": true) now stream Server-Sent Events end-to-end. Prior versions could panic or return an empty body for streaming requests; non-streaming requests were not affected.
Streaming request handling no longer captures recycled Fiber context state in its background writer goroutine.
The streaming code path now owns its own request context lifecycle, eliminating premature context cancellation after the HTTP handler returned.
Compatibility API surface is unchanged from v1.0.0 (OpenAI-compatible /v1/chat/completions, /healthz, /readyz, /version, /metrics). Database schema is unchanged; no migration required. Configuration variables and Docker image entrypoint are unchanged.
Recommended action Customers running v1.0.0 should upgrade by pulling tag 1.0.2 and restarting their container against the same PostgreSQL and Redis instances. No data migration is required. Do not deploy 1.0.1 it is a withdrawn intermediate build that does not contain the complete streaming fix.
Additional details
Usage instructions
AFTER SUBSCRIBING
- Pull the container image:
docker pull 709825985650.dkr.ecr.us-east-1.amazonaws.com/gj-sev/swn-ai-gateway:1.0.2
- Ensure the following services are available:
-
PostgreSQL 14+
-
Redis 6+
-
At least one provider API key:
- OpenAI
- Anthropic
- Google Gemini
- Configure required environment variables:
- DATABASE_URL
- REDIS_URL
- AEGIS_OPENAI_API_KEY
- AEGIS_ANTHROPIC_API_KEY
- AEGIS_GEMINI_API_KEY
Example:
DATABASE_URL=postgres://user:pass@host:5432/aegis?sslmode=require REDIS_URL=redis://host:6379/0
- Start the container:
docker run -d --name swn-ai-gateway -p 8080:8080 -e DATABASE_URL="postgres://user:pass@db-host:5432/aegis?sslmode=require" -e REDIS_URL="redis://redis-host:6379/0" -e AEGIS_OPENAI_API_KEY="sk-..." 709825985650.dkr.ecr.us-east-1.amazonaws.com/gj-sev/swn-ai-gateway:1.0.2
- Verify deployment:
curl http://SERVER_IP:8080/healthz curl http://SERVER_IP:8080/readyz
- Create an API key:
docker exec -it swn-ai-gateway ./aegis-gateway keys create --org-name my-company --key-name production
- Send requests to the OpenAI-compatible endpoint:
POST /v1/chat/completions
Example:
curl https://your-host/v1/chat/completions -H "Authorization: Bearer aegis_sk_..." -H "x-provider: openai" -H "x-model: gpt-4o-mini" -H "Content-Type: application/json" -d '{"messages":[{"role":"user","content":"Hello"}]}'
SUPPORTED FEATURES
- OpenAI-compatible API
- Streaming responses
- Provider fallback
- Rate limiting
- Prometheus metrics
- Structured JSON logging
MONITORING ENDPOINTS
- GET /healthz
- GET /readyz
- GET /metrics
- GET /version
Deployment templates, ECS task definitions, Kubernetes manifests, Docker Compose examples, and installation resources are available at:
SWN AI Gateway Deployment Resources
UPGRADE
- Back up PostgreSQL.
- Pull the latest image.
- Restart the container using the same DATABASE_URL and REDIS_URL.
SUPPORT Website: https://swnllc.io
Email: support@swnllc.io
Support
Vendor support
Support Email: support@swnllc.io
Documentation and onboarding support are available for enterprise deployments, Kubernetes integrations, and infrastructure setup assistance.
Website: https://swnllc.io
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.
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.