mlsanityData to 7 Oct 2026

This Is Taking Too Long -- Investigating Time as a Proxy for Energy Consumption of LLMs

arXiv 2603.15699 ↗First posted 16 Mar 2026cs.PF cs.AI cs.SEcited by 3

Not on the map. Why?

Abstract (arXiv)

The energy consumption of Large Language Models (LLMs) is raising growing concerns due to their adverse effects on environmental stability and resource use. Yet, these energy costs remain largely opaque to users, especially when models are accessed through an API -- a black box in which all information depends on what providers choose to disclose. In this work, we investigate inference time measurements as a proxy to approximate the associated energy costs of API-based LLMs. We ground our approach by comparing our estimations with actual energy measurements from locally hosted equivalents. Our results show that time measurements allow us to infer GPU models for API-based LLMs, grounding our energy cost estimations. Our work aims to create means for understanding the associated energy costs of API-based LLMs, especially for end users.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 19 of its 34 references that are in the map. First posted on arXiv 16 Mar 2026.

Builds on

19 of 34 references.

References · 19

  1. 2017Attention Is All You Needcited by 59,932
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2024The Llama 3 Herd of Modelscited by 14,192
  4. 2025Qwen3 Technical Reportcited by 8,195
  5. 2021Carbon Emissions and Large Neural Network Trainingcited by 561
  6. 2020Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learningcited by 246
  7. 2021Sustainable AI: Environmental Implications, Challenges and Opportunitiescited by 242
  8. 2024LiveBench: A Challenging, Contamination-Limited LLM Benchmarkcited by 242
  9. 2020Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Modelscited by 168
  10. 2023From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inferencecited by 168
  11. 2025How Hungry is AI? Benchmarking Energy, Water, and Carbon Footprint of LLM Inferencecited by 73
  12. 2021Compute and Energy Consumption Trends in Deep Learning Inferencecited by 61
7 more
  1. 2025Artificial Intelligence Index Report 2025cited by 58
  2. 2025Energy Considerations of Large Language Model Inference and Efficiency Optimizationscited by 54
  3. 2024The Ethics of ChatGPT in Medicine and Healthcare: A Systematic Review on Large Language Models (LLMs)cited by 45
  4. 2025Quantifying the Energy Consumption and Carbon Emissions of LLM Inference via Simulationscited by 12
  5. 2024The Power of Training: How Different Neural Network Setups Influence the Energy Demandcited by 7
  6. 2023A Green(er) World for A.Icited by 5
  7. 2025Promoting Sustainable Web Agents: Benchmarking and Estimating Energy Consumption through Empirical and Theoretical Analysiscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026The Energy Footprint of LLM-Based Environmental Analysis: LLMs and Domain Productscited by 2
  2. 2026WattGPU: Predicting Inference Power and Latency on Unseen GPUs and LLMscited by 1
  3. 2026Multi-Level Modeling of Large Language Model Inference Latency and Energy via Hybrid Analytical--Machine-Learning Predictorscited by 0