Integrations & Cost
Published 2026-04-20Updated 2026-07-132 min read
Overviewโ
Covers external AWS service integrations and cost analysis. Includes SageMaker-EKS hybrid training and inference patterns, Langfuse, Prometheus, AMP/AMG-based Observability stack deployment, coding tools (Aider, Cline, Cursor) cost analysis, and other platform peripheral integrations.
What This Section Coversโ
- SageMaker-EKS Integration -- Hybrid architecture patterns combining SageMaker training with EKS inference
- Monitoring Stack Setup -- Langfuse Helm deployment, AMP/AMG, and OTel integration
- Open-Weight Model Deployment Guide -- Self-hosting decisions from token economics and data sovereignty perspectives
- Coding Tools Cost Analysis -- Cost structure comparison of Aider, Cline, and Cursor
Related Documentsโ
- Inference Gateway Deployment -- Gateway infrastructure configured before these integrations
- Model Lifecycle -- Where SageMaker and monitoring integrations fit in training/deployment pipelines
- Agent Monitoring -- Operating the observability stack after deployment
Document Listโ
๐๏ธ SageMaker-EKS Integration
A hybrid ML architecture that trains on SageMaker and serves on EKS
๐๏ธ Monitoring
Hands-on setup guide for integrated monitoring with Prometheus to AMP, AMG, Langfuse, and Bifrost OTel
๐๏ธ Cost & IDE
Aider, Cline, Continue.dev integration + Bedrock vs Kiro vs self-hosting cost comparison
๐๏ธ Open-Weight Model Deployment
A customer-facing decision guide for evaluating and choosing self-hosted open-weight LLM deployment from the perspectives of token economics and data sovereignty.