If you run claude against Amazon Bedrock across a dozen repos, your bill arrives as one opaque number. Until recently, the workaround was clunky — create an application inference profile per project, swap them by hand, hope you remembered which one was active. In April 2026, AWS shipped native per-principal cost …

Choosing a vector store on AWS for generative AI (GenAI) workloads used to be a one-line decision: pick Amazon OpenSearch Service or its serverless variant (AOSS) and move on. That changed when Amazon S3 Vectors went GA in 2025. By storing vector data directly in S3 and pricing it on a fully consumption-based model, S3 …