Tools

Directional calculators for AI compute decisions.

These tools keep the math visible and estimate-labeled. Replace defaults with current provider pricing, quotes, logs, and bills before making a buying decision.

By Andrew Cooper, Founder of RunPlacement Updated May 2026 Provider-neutral, estimate-labeled guidance Verify current provider pricing

Available now

AI inference cost

Start here when API spend, managed serving, or self-hosted GPU cost is becoming a real product margin question.

Interactive calculatorAI Inference Cost CalculatorCompare API, managed inference, and self-hosted GPU cost by request volume, tokens, idle capacity, utilization, and ops overhead.

Supporting pages

Read the framework after the estimate

The calculator is most useful when paired with plain-English definitions and decision pages.

FrameworkAI Inference Cost ModelNormalize serving options by effective cost per successful request. Decision pageAPI vs Self-Hosted InferencePrice control, utilization, idle capacity, and operations. Decision pageManaged Inference vs GPU CloudCompare platform premium against support, autoscaling, batching, and control.