Framework library
Definitions and formulas for infrastructure decisions.
These pages turn RunPlacement's decision model into usable concepts: workload placement, useful GPU-hours, cloud bill shock taxonomy, cloud exit payback, and infrastructure control premium.
AI inference cost
AI inference cost frameworks
API, managed inference, self-hosted GPU, batch, realtime, and hybrid serving cost decisions.
Workload placement
Workload placement frameworks
The baseline worksheet for choosing a placement category before comparing vendors.
Choose workload placement by matching the workload's cost driver, data movement, performance needs, operational tolerance, and commitment horizon to the right infrastructure category.
Workload placementManaged Platform vs Infrastructure Control Frameworkinfrastructure control premiumA managed platform is better when it removes operational work the team should not own; direct infrastructure is better when control creates enough performance, cost, or compliance value to justify the burden.
GPU pricing
GPU pricing frameworks
Quote review, useful GPU-hours, data movement, utilization, and provider tradeoffs.
Useful GPU-hour cost is the better comparison unit when GPU providers differ in utilization, queueing, reliability, storage behavior, or operational model.
Worked examplesUseful GPU-Hour ExamplesHypothetical GPU cost scenariosFive labeled examples showing how retries, idle time, data staging, and utilization can change effective GPU cost.
AWS bill shock
AWS bill shock frameworks
Line-item triage before assuming the whole cloud placement is wrong.
Cloud migration
Cloud migration frameworks
Exit costs, payback windows, portability, and partial move decisions.