# Greening AI Inference with Accuracy and Latency-aware User Incentives

arXiv: https://arxiv.org/abs/2605.27309 · HTML: https://mlsanity.com/paper/2605.27309/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 23 references that are in the map.
- First posted on arXiv 26 May 2026.

## Builds on (most cited first, 9 of 9)

- [Sustainable AI: Environmental Implications, Challenges and Opportunities](https://mlsanity.com/paper/2111.00364/) (2021)
- [How Hungry is AI? Benchmarking Energy, Water, and Carbon Footprint of LLM Inference](https://mlsanity.com/paper/2505.09598/) (2025)
- [Measuring the environmental impact of delivering AI at Google Scale](https://mlsanity.com/paper/2508.15734/) (2025)
- [EcoServe: Designing Carbon-Aware AI Inference Systems](https://mlsanity.com/paper/2502.05043/) (2025)
- [Clover: Toward Sustainable AI with Carbon-Aware Machine Learning Inference Service](https://mlsanity.com/paper/2304.09781/) (2023)
- [One Size Does Not Fit All: Quantifying and Exposing the Accuracy-Latency Trade-off in Machine Learning Cloud Service APIs via Tolerance Tiers](https://mlsanity.com/paper/1906.11307/) (2019)
- [Reconciling High Accuracy, Cost-Efficiency, and Low Latency of Inference Serving Systems](https://mlsanity.com/paper/2304.10892/) (2023)
- [MOSEL: Inference Serving Using Dynamic Modality Selection](https://mlsanity.com/paper/2310.18481/) (2023)
- [Carbon-Aware Quality Adaptation for Energy-Intensive Services](https://mlsanity.com/paper/2411.19058/) (2024)

## Abstract (arXiv)

The widespread use of AI services has raised concerns for its environmental sustainability, towards which recent studies have identified carbon emissions of AI inference as the major contributor. This paper introduces a framework for designing AI inference incentives based on the users' valuation for inference quality and latency, together with their environmental consciousness, while accounting for the tradeoff between carbon emissions and the two QoE parameters. Our approach can accommodate different tradeoffs, that depend on the size and complexity of the AI models and the allocation of resources to serve inference requests. The incentives can be offered through a practical two-tier service subscription that offers users a discount in exchange for reduced carbon emissions. The discounted service option gives the AI provider the flexibility to serve some percentage of inference requests at a lower quality and higher latency during periods of high carbon intensity.