Methodology

How every number on this site is calculated, and where the data comes from.

Our Approach

Know Your Compute provides transparent, data-backed estimates of the environmental cost of AI inference.

We prioritise official disclosures from providers, then peer-reviewed academic research, then transparent estimation. We never present a guess as a fact — every figure on this site shows its confidence level.

All calculations cover inference only (the energy used when you interact with a model), not training. We focus on per-query impact because inference now accounts for 80–90% of AI's total energy consumption.

Data Source Tiers

Verified

Tier 1 — Verified

Official disclosures from providers:

Peer-reviewed

Tier 2 — Peer-reviewed

Published academic research:

Estimated

Tier 3 — Estimated

Our estimation framework, based on:

  • GPU system power specifications (NVIDIA H100, Google TPU)
  • API performance benchmarks (latency, throughput)
  • Regional environmental multipliers (PUE, WUE, CIF)

The Estimation Formula

For models without official disclosures, we estimate energy per query as:

E_query = (P_gpu × N_gpu × T_inference × PUE) / 3600
E_query
Energy per query in watt-hours (Wh)
P_gpu
GPU system power in watts, including server overhead (~1.72× the GPU's rated TDP)
N_gpu
Number of GPUs needed per query (derived from model size and memory requirements)
T_inference
Inference time in seconds (from API benchmarks or throughput estimates)
PUE
Power Usage Effectiveness of the data centre (1.0 = perfect, typical is 1.1–1.35)

CO₂ and water are then derived from energy using regional environmental data:

CO₂ (grams) = E_query × CIF / 1000
Water (mL) = E_query × (site_WUE + source_WUE)

Regional Environmental Data

Environmental impact varies significantly by inference location. We use these regional factors:

RegionCIF (gCO₂/kWh)PUESite WUE (L/kWh)Source WUE (L/kWh)
Azure US East (Virginia)4501.180.301.50
Azure Sweden251.150.100.20
Google Global1301.11.080.80
AWS US East3501.150.201.30
China (general)5501.351.502.00
xAI Memphis3801.250.501.40

Limitations

  • We measure inference only, not training or hardware manufacturing
  • Energy consumption varies 10–100× by prompt length and complexity
  • Provider disclosures may undercount overhead (cooling, networking, storage)
  • Self-hosted model data depends on your hardware and electricity source
  • Water and CO₂ figures are derived from energy using regional averages — actual values vary by time of day and season
  • We update data periodically; real-world efficiency improves continuously

Data last reviewed: March 2026

Calculate My Compute