AI inference glossary
Benchmark metrics

Performance per dollar

Also known as perf/$, cost efficiency

In plain English

Performance per dollar measures how much useful AI output the system produces for each dollar spent running it.

Technical definition

Performance per dollar expresses how much measured inference work a system delivers for a unit of modeled cost.

Engineering details

For a fixed workload and interactivity target, performance per dollar is the inverse of cost per token. A 2× perf/$ advantage means the system can produce about twice as many comparable tokens for the same infrastructure spend.

Why it matters

Peak chip FLOPS account for only part of serving economics. Memory, networking, software maturity, numerical precision, and achievable utilization all affect the measured output behind the ratio.

How to read it in InferenceX

InferenceX compares perf/$ at matched interactivity and names the TCO inputs used. Ratios should not be carried across different model, sequence-length, precision, or latency regimes.