Guides
Buyer guides
Evergreen guides for teams choosing where to run LLMs under regulatory constraints. Each guide links back to the vendor data and cites primary sources for every rule it describes.
-
Azure OpenAI PTU explained: provisioned throughput vs pay-as-you-go, pricing model, global/data-zone/regional deployments
What an Azure OpenAI PTU buys, how it is billed against pay-as-you-go, what it costs at published rates, and where Global, Data Zone and Regional deployments process data.
-
Amazon Bedrock provisioned throughput: model units, commitment terms, pricing
How Amazon Bedrock Provisioned Throughput works: what a model unit buys, the three commitment terms, how it is billed and what AWS publishes about price.
-
Provisioned throughput vs pay-per-token for LLM serving
Reserved LLM capacity against per-token billing: what each buys, the units and terms each vendor uses, and how to work out which is cheaper for your traffic.
-
Data residency vs data sovereignty vs operational sovereignty
Data residency is where data sits. Data sovereignty is whose law governs it. Operational sovereignty is who can run and reach the system. Three terms, three questions, kept apart.
-
What is Single-Tenant LLM Hosting?
A definitional guide to single-tenant LLM hosting: what it is, why it matters now, and which deployment models actually qualify.
In preparation
- Buying single-tenant LLM hosting in the UK public sector
- Dedicated LLM hosting for FCA-regulated firms
- Hosting LLMs on NHS and health data
- Total cost of ownership: dedicated vs shared inference