Optimizing Deepseek Chat API Costs Based on Log Pattern Analysis using Business Intelligence and CRISP-DM
Abstract
This study aims to analyze token usage and cost patterns of the DeepSeek Chat API and formulate cost optimization strategies based on historical log data. The study employs a Business Intelligence approach with the CRISP-DM framework through descriptive and diagnostic analysis of usage data from July 9 to November 30, 2025. The analysis covers token usage, cost, cost per token, usage patterns over time, correlation, and context caching. The results show a total usage of 81,612,706 tokens with a total cost of USD 11.212044 and an average daily usage of 562,846.25 tokens. The aggregate cost per million tokens was USD 0.137381, while the Pearson correlation between token usage and cost was 0.791494. Context caching analysis showed a cache hit rate of 83.97% and a cache miss rate of 16.03%. Based on the analysis, usage patterns with relatively higher costs can be identified to support token volume monitoring and the utilization of context caching as part of cost optimization strategies. The results are presented through a Business Intelligence dashboard as a tool for monitoring and evaluating DeepSeek Chat API usage.
References
Aldhafeeri, L., Aljumah, F., Thabyan, F., Alabbad, M., AlShahrani, S., Alanazi, F., & Al-Nafjan, A. (2025). Generative AI chatbots across domains: A systematic review. Applied Sciences, 15(20), 11220. https://doi.org/10.3390/app152011220
Atmauswan, P. S., & Abdullahi, A. M. (2022). Intelligent chatbot for university information system using natural language approach. Albukhary Social Business Journal, 59-64. https://doi.org/10.55862/asbjv3i2a007
Balasingam, I. (2022). A review of business analytics methods. International Journal on Research and Development—A Management Review, 11(1), 129–132. https://doi.org/10.65521/ijrdmr.v11i1.1778
Budiman, A. A., Yudha, A., & Utomo, C. S. (2021). Pembuatan Sistem Chatbot Menggunakan Metode Contextual. Jurnal Sains & Teknologi Fakultas Teknik Universitas Darma Persada, 11(2), 20-24. https://doi.org/10.70746/jstunsada.v11i2.157
Burnay, C., Lega, M., & Bouraga, S. (2024). Business intelligence and cognitive loads: Proposition of a dashboard adoption model. Data & Knowledge Engineering, 152, 102310. https://doi.org/10.1016/j.datak.2024.102310
Caldarini, G., Jaf, S., & McGarry, K. (2022). A literature survey of recent advances in chatbots. Information, 13(1), 41. https://doi.org/10.3390/info13010041
Cusumano, M. A. (2025). DeepSeek inside: origins, technology, and impact. Communications of the ACM, 68(7), 18-22. https://doi.org/10.1145/3732796
Florensia, N. P., Safa, Y. N., Patimah, Y., Priskila, R., & Pranatawijaya, V. H. (2024). Implementasi Open AI pada website restoran makanan India. JATI (Jurnal Mahasiswa Teknik Informatika), 8(3), 3766-3772. https://doi.org/10.36040/jati.v8i3.9770
Gao, J., Cao, Z., & Li, W. (2024). Selfcp: Compressing over-limit prompt via the frozen large language model itself. Information Processing & Management, 61(6), 103873. https://doi.org/10.1016/j.ipm.2024.103873
Guo, D., Yang, D., Zhang, H., Song, J., Wang, P., Zhu, Q., ... & Tan, Y. (2025). DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning. Nature, 645(8081), 633-638. https://doi.org/10.1038/s41586-025-09422-z
Habieby, N. (2026). Workload Analysis Using The FT (Full Time Equivalent) Method To Determine The Effective Employee Requirements At Pt. Bank Rakyat Indonesia. Techne: Journal of Engineering, Technology and Industrial Applications, 2(2), 1-9.
Hjelle, S., Mikalef, P., Altwaijry, N., & Parida, V. (2024). Organizational decision making and analytics: An experimental study on dashboard visualizations. Information & Management, 61(6), 104011. https://doi.org/10.1016/j.im.2024.104011
Jin, I., Tangsrivimol, J. A., Darzi, E., Hassan Virk, H. U., Wang, Z., Egger, J., ... & Krittanawong, C. (2025). DeepSeek vs. ChatGPT: prospects and challenges. Frontiers in Artificial Intelligence, 8, 1576992. https://doi.org/10.3389/frai.2025.1576992
Laymouna, M., Ma, Y., Lessard, D., Schuster, T., Engler, K., & Lebouché, B. (2024). Roles, users, benefits, and limitations of chatbots in health care: rapid review. Journal of medical Internet research, 26, e56930. https://doi.org/10.2196/56930
Maksymenko, D., & Turuta, O. (2025). Tokenization efficiency of current foundational large language models for the Ukrainian language. Frontiers in artificial intelligence, 8, 1538165. https://doi.org/10.3389/frai.2025.1538165
Martínez-Plumed, F., Contreras-Ochando, L., Ferri, C., Hernández-Orallo, J., Kull, M., Lachiche, N., ... & Flach, P. (2019). CRISP-DM twenty years later: From data mining processes to data science trajectories. IEEE transactions on knowledge and data engineering, 33(8), 3048-3061. https://doi.org/10.1109/TKDE.2019.2962680
Mekimah, S., Zighed, R., Mili, K., & Bengana, I. (2024). Business intelligence in organizational decision-making: a bibliometric analysis of research trends and gaps (2014–2024). Discover Sustainability, 5(1), 532. https://doi.org/10.1007/s43621-024-00692-7
Michael, C. I., Ipede, O. J., Adejumo, A. D., Adenekan, I. O., Adebayo, D., Ojo, A. S., & Ayodele, P. A. (2024). Data-driven decision making in IT: Leveraging AI and data science for business intelligence. World Journal of Advanced Research and Reviews, 23(01), 432-439. https://doi.org/10.30574/wjarr.2024.23.1.2010
Mishra, R., Kaur, I., Sahu, S., Saxena, S., Malsa, N., & Narwaria, M. (2023). Establishing three layer architecture to improve interoperability in Medicare using smart and strategic API led integration. SoftwareX, 22, 101376.
Nugraha, Y., Masnita, Y., & Kurniawati, K. (2022). Peran responsiveness chatbot artificial intelligence dalam membentuk customer satisfaction. Jurnal Manajemen Dan Bisnis Sriwijaya, 20(3), 143-158. https://doi.org/10.29259/jmbs.v20i3.18528
Nugroho, A. W., & Utama, A. A. G. S. (2025). Business intelligence systems and their impact on organizational decision-making and performance outcomes: Literature review. Owner: Riset dan Jurnal Akuntansi, 9(2), 1269-1284. https://doi.org/10.33395/owner.v9i2.2646
Plotnikova, V., Dumas, M., Nolte, A., & Milani, F. (2023). Designing a data mining process for the financial services domain. Journal of Business Analytics, 6(2), 140-166. 140–166. https://doi.org/10.1080/2573234X.2022.2088412
Sousa, B., Guerreiro, G. R., & Espadinha-Cruz, P. (2026). From fragmented data to business intelligence: a data-centric CRISP-DM framework for delegated insurance. Information Systems and e-Business Management, 1-28. https://doi.org/10.1007/s10257-026-00729-6
Staudinger, S., Schuetz, C. G., Schrefl, M., & Neuböck, T. (2025). Knowledge graph support for descriptive business analytics. DECISION, 52(3), 285-306. https://doi.org/10.1007/s40622-025-00432-4
Xu, Z., Liu, S., Huang, W., Shi, J., Xu, F., Tang, X., & Lu, H. (2025). Deepseek: implications for data science and management in the AI era. Data Science and Management. https://doi.org/10.1016/j.dsm.2025.09.001
Zehle, T., Schlager, M., Heiß, T., & Feurer, M. (2025). CAPO: Cost-aware prompt optimization. arXiv preprint arXiv:2504.16005. https://proceedings.mlr.press/v293/zehle25a.html
Copyright (c) 2026 International Journal of Science and Society
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
.png)
.jpg)
.png)
.png)
.png)
.png)
1.png)
.jpg)
-modified.png)
-modified.png)
-modified.png)
