Reducing Artificial Intelligence Costs in Business through Prompt Optimization
Main Article Content
Abstract
This study investigates the optimization of token consumption in large language models (LLMs) through prompt engineering, specifically comparing full-sentence prompts with keyword-based alternatives. Analyzing data from multiple LLM providers across four task types (Question-Answer, Duty, Summary, and Creativity), the research examined token usage patterns and response quality metrics. The study utilized a comprehensive dataset (N=1,231) and employed various evaluation methods, including BERTScore, ROUGE-L, and perplexity analysis. Results demonstrated significant token savings with keyword-based prompts (reduction in cost of 16,7%) while maintaining comparable response quality. Analysis revealed task-specific variations in performance, with duty-related tasks showing no significant quality degradation, while question-answering and summary tasks exhibited minimal quality differences. The findings suggest that keyword-based prompting offers a viable cost optimization strategy for businesses implementing LLM solutions, particularly in duty-related applications. Statistical analysis confirmed significant differences in token consumption (p < .001) with substantial effect sizes, while quality metrics showed only marginal decreases in semantic similarity (ΔBERTScore = -0.005) and surface-level similarity (ΔROUGE-L = -0.019). This research provides practical insights for organizations seeking to optimize their LLM implementation costs while maintaining response quality.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
References
O. Ahia, S. Kumar, H. Gonen, J. Kasai, D. R. Mortensen, N. A. Smith, and Y. Tsvetkov, (2023). Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models. EMNLP, pp. 9904-9923.
E. Alexandrova, M. Poddubnaya, K. Shalenaya, and S. M. Savvidi, (2019). Opportunities of the Digital Economy for Achieving Competitive Advantage of Firms. AEBMR.
F. T. Awamleh and A. N. Bustami, (2022). Examine the Mediating Role of the Information Technology Capabilities on the Relationship Between Artificial Intelligence and Competitive Advantage During the COVID-19 Pandemic. SAGE Publishing, vol. 12(3).
L. Beurer-Kellner, M. L. Fischer, and M. Vechev, (2022). Prompting Is Programming: A Query Language for Large Language Models. Cornell University.
A. F. Borges, F. J. Laurindo, M. D. M. Spínola, R. F. Gonçalves, and C. A. D. Mattos, (2020). The strategic use of artificial intelligence in the digital era: Systematic literature review and future research directions. Elsevier BV, vol. 57.
J. Bughin, E. Hazan, S. Ramaswamy, M. Chui, T. Allas, P. Dahlström, N. Henke, and M. Trench, (2017). Artificial intelligence: the next digital frontier?.
S. Burdon, K. Kang, and G. Mooney, (2016). Understanding The Key Attributes for a Successful Innovation Culture. IGI Global, vol. 12(4), pp. 70-82.
C. Y. T. Chan and D. Petrikat, (2023). Strategic Applications of Artificial Intelligence in Healthcare and Medicine. JMHS, vol. 4(3), pp. 58-68.
L. Chen, M. Zaharia, and J. Zou, (2023). FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance. Cornell University.
X. Cheng, L. Xiao, X. Shen, A. Zarifis, and J. Mou, (2022). The dark sides of AI. Springer Science+Business Media, vol. 32(1), pp. 11-15.
A. Chernov, V. A. Chernova, and T. Komarova, (2020). The Usage of Artificial Intelligence in Strategic Decision Making in Terms of Fourth Industrial Revolution.
J. Cohen, T. Cao, J. D. Viviano, C. Huang, M. Fralick, M. Ghassemi, M. Mamdani, R. Greiner, and Y. Bengio, (2021). Problems in the deployment of machine-learned models in health care. Canadian Medical Association, vol. 193(35), pp. E1391-E1394.
J. Cunningham, J. Farquharson, and D. Hull, (1991). A profile of the human fears of technological change. Elsevier BV, vol. 40(4), pp. 355-370.
I. Cuypers, J. Hennart, B. S. Silverman, and G. Ertug, (2020). Transaction Cost Theory: Past Progress, Current Challenges, and Suggestions for the Future. Routledge, vol. 15(1), pp. 111-150.
I. M. Enholm, E. Papagiannidis, P. Mikalef, and J. Krogstie, (2021). Artificial Intelligence and Business Value: a Literature Review. Springer Science+Business Media, vol. 24(5), pp. 1709-1734.
J. Furman and R. Seamans, (2018). AI and the Economy. University of Chicago Press, vol. 19, pp. 161-191.
D. Herremans, (2021). aiSTROM–A Roadmap for Developing a Successful AI Strategy. Institute of Electrical and Electronics Engineers, vol. 9.
J. Holmström, (2021). From AI to digital transformation: The AI readiness framework. Elsevier BV, vol. 65(3), pp. 329-339.
R. Indjikian and D. S. Siegel, (2005). The Impact of Investment in IT on Economic Performance: Implications for Developing Countries. Elsevier BV, vol. 33(5), pp. 681-700.
M. Joshi, (2025). Retraining US Workforce in the Age of Agentic Gen AI: Role of Prompt Engineering and Up-Skilling Initiatives. International Journal of Advanced Research in Science, Communication and Technology, vol. 17(1), pp. 1-10.
J. Kaddour, J. Harris, M. Mozes, H. Bradley, R. Raileanu, and R. McHardy, (2023). Challenges and Applications of Large Language Models. Cornell University.
K. Kobelsky, V. J. Richardson, R. E. Smith, and R. W. Zmud, (2008). Determinants and Consequences of Firm Information Technology Budgets. American Accounting Association, vol. 83(4), pp. 957-995.
A. K. Kordon, (2020). Applied Artificial Intelligence-Based Systems as Competitive Advantage. IEEE, vol. 77, pp. 6-18.
A. Kumar and A. Kalse, (2021). Usage and adoption of artificial intelligence in SMEs.
J. Lee, T. Suh, D. Roy, and M. S. Baucus, (2019). Emerging Technology and Business Model Innovation: The Case of Artificial Intelligence. Springer Science+Business Media, vol. 5(3), pp. 44-44.
D. Mikhailov, (2023). Optimizing National Security Strategies through LLM-Driven Artificial Intelligence Integration.
N. E. Moukhi, I. E. Azami, and A. Mouloudi, (2015). Data warehouse state of the art and future challenges.
A. Mudrik, et al., (2025). Prompt Engineering in Large Language Models for Patient Education: A Systematic Review. medRxiv.
W. Reim, J. Åström, and O. Eriksson, (2020). Implementation of Artificial Intelligence (AI): A Roadmap for Business Model Innovation. Multidisciplinary Digital Publishing Institute, vol. 1(2), pp. 180-191.
A. Sánchez-Comas, L. E. V. Osorio, M. Pérez-Vargas, M. Caicedo-García, D. N. Rodado, and A. T. Palacio, (2020). Diagnostic tool for radical improvement in business processes. IOP Publishing, vol. 844(1).
O. Sharir, B. Peleg, and Y. Shoham, (2020). The Cost of Training NLP Models: A Concise Overview. Cornell University.
S. Shekhar, T. Dubey, K. Mukherjee, A. Saxena, A. Tyagi, and N. Kotla, (2024). Towards Optimizing the Costs of LLM Usage. Cornell University.
E. Strubell, A. Ganesh, and A. McCallum, (2019). Energy and Policy Considerations for Deep Learning in NLP.
A. Subramanian, L. D. Smith, A. C. Nelson, J. F. Campbell, and D. A. Bird, (1997). Strategic planning for data warehousing. Elsevier BV, vol. 33(2), pp. 99-113.
R. Szilágyi and M. Tóth, (2023). Use of LLM for SMEs, opportunities and challenges. Journal of Agricultural Informatics, vol. 14(2), pp. 23-32.
M. U. Tariq, M. Poulin, and A. A. Abonamah, (2021). Achieving Operational Excellence Through Artificial Intelligence: Driving Forces and Barriers. Frontiers Media, vol. 12.
D. Tjondronegoro, E. Yuwono, B. Richards, D. Green, and S. Hatakka, (2022). Responsible AI Implementation: A Human-centered Framework for Accelerating the Innovation Process. Cornell University.
K. R. Varshney and H. Alemzadeh, (2016). On the Safety of Machine Learning: Cyber-Physical Systems, Decision Sciences, and Data Products. Cornell University.
S. Verma, R. Sharma, S. Deb, and D. Maitra, (2021). Artificial intelligence in marketing: Systematic review and future research direction. Elsevier BV, vol. 1(1), pp. 100002-100002.
D. N. Wagner, (2020). Strategically managing the artificially intelligent firm. Emerald Publishing Limited, vol. 48(3), pp. 19-25.
J. Wang, E. Shi, S. Yu, Z. Wu, C. Ma, H. Dai, Q. Yang, Y. Kang, J. Wu, H. Hu, C. Yue, H. Zhang, Y. Liu, X. Li, B. Ge, D. Zhu, Y. Yuan, D. Shen, T. Liu, and S. Zhang, (2023). Prompt Engineering for Healthcare: Methodologies and Applications. Cornell University.
Y. Weng, J. Wu, T. Kelly, and W. Johnson, (2024). Comprehensive Overview of Artificial Intelligence Applications in Modern Industries.
Y. Zhang and S. Jin, (2023). How Does Digital Transformation Increase Corporate Sustainability? The Moderating Role of Top Management Teams. Multidisciplinary Digital Publishing Institute, vol. 11(7), pp. 355-355.
A. White, et al., (2023). A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT. arXiv.
V. Liagkou, E. Filiopoulou, G. Fragiadakis, M. Nikolaidou, & C. Michalakelis. (2024). The Cost Perspective of Adopting Large Language Model-as-a-Service. Proceedings of the IEEE Joint Conference on Cloud Computing, 1-12. https://doi.org/10.1109/JCC.2024.1234567