Private AI for Financial Data: Residency, Routing and Cost on AWS Bedrock, Microsoft Azure and Your Own GPUs
Billing models and idle cost, per-call cost at three volumes, Bedrock in-region vs EU profiles, Converse API with prompt caching and IAM region enforcement, Azure deployment types and Claude on Foundry, UK and EU providers, a residency-aware provider registry, cost-cutting workflow, a golden-set evaluation harness and GPU break-even