Beyond Benchmarks: The Economics of AI Inference
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909878012870656 |
|---|---|
| author | Zhuang, Boqin Qiao, Jiacheng Liu, Mingqian Yu, Mingxing Hong, Ping Li, Rui Song, Xiaoxia Xu, Xiangjun Chen, Xu Ma, Yaoyao Gao, Yujie |
| author_facet | Zhuang, Boqin Qiao, Jiacheng Liu, Mingqian Yu, Mingxing Hong, Ping Li, Rui Song, Xiaoxia Xu, Xiangjun Chen, Xu Ma, Yaoyao Gao, Yujie |
| contents | The inference cost of Large Language Models (LLMs) has become a critical factor in determining their commercial viability and widespread adoption. This paper introduces a quantitative ``economics of inference'' framework, treating the LLM inference process as a compute-driven intelligent production activity. We analyze its marginal cost, economies of scale, and quality of output under various performance configurations. Based on empirical data from WiNEval-3.0, we construct the first ``LLM Inference Production Frontier,'' revealing three principles: diminishing marginal cost, diminishing returns to scale, and an optimal cost-effectiveness zone. This paper not only provides an economic basis for model deployment decisions but also lays an empirical foundation for the future market-based pricing and optimization of AI inference resources. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_26136 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Beyond Benchmarks: The Economics of AI Inference Zhuang, Boqin Qiao, Jiacheng Liu, Mingqian Yu, Mingxing Hong, Ping Li, Rui Song, Xiaoxia Xu, Xiangjun Chen, Xu Ma, Yaoyao Gao, Yujie Artificial Intelligence The inference cost of Large Language Models (LLMs) has become a critical factor in determining their commercial viability and widespread adoption. This paper introduces a quantitative ``economics of inference'' framework, treating the LLM inference process as a compute-driven intelligent production activity. We analyze its marginal cost, economies of scale, and quality of output under various performance configurations. Based on empirical data from WiNEval-3.0, we construct the first ``LLM Inference Production Frontier,'' revealing three principles: diminishing marginal cost, diminishing returns to scale, and an optimal cost-effectiveness zone. This paper not only provides an economic basis for model deployment decisions but also lays an empirical foundation for the future market-based pricing and optimization of AI inference resources. |
| title | Beyond Benchmarks: The Economics of AI Inference |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2510.26136 |