Inference Tokens per Watt Calculator: AI Serving Energy & Cost
Training is a one-time burst of compute. Inference — serving a model to millions of users around the clock — is the ongoing cost that actually defines the economics of an AI product. Tokens-per-watt-hour is becoming the standard efficiency metric for AI services: it captures both the throughput of the hardware and the power it draws to produce that throughput. This calculator estimates your inference energy efficiency and translates it into the number that shows up on the cloud bill: cost per million tokens.
1 ÷ (power × PUE ÷ tps ÷ 3600)
watt-hours to generate 1k tokens
at selected electricity rate
4,000 kWh at 50,000M tokens
serving cost at volume
Results update live as you type. For planning and field-check estimates — always verify against applicable standards and equipment ratings.
How we calculate this →From watts and throughput to tokens per watt-hour
The math starts with one question: how much energy does one token cost? Power draw (watts) times PUE gives total facility power attributable to this serving node. Dividing by tokens-per-second gives watt-seconds per token, and dividing by 3,600 converts to watt-hours per token — the natural unit for energy cost accounting. Flipping that gives tokens per watt-hour, the efficiency headline.
Cost per million tokens is the commercial translation: multiply kWh per token by one million, then by the electricity rate. At $0.08/kWh and a modest 5,000 tok/s serving rate at 1,200 W with a 1.2 PUE, energy cost alone is roughly $0.046 per million tokens — a fraction of the API prices cloud providers charge, but a real and growing line item as inference volumes scale.
Monthly cost scales directly with volume. At 50 billion tokens per month (50,000 M), that same setup draws about 320 MWh and costs roughly $25,600 in electricity alone — before amortized hardware, bandwidth, or labor. Understanding this per-token energy cost is the first step toward optimizing model serving: smaller models, quantization, speculative decoding, and batching all improve the tokens-per-watt figure and reduce cost at scale.