隨著生成式人工智慧技術快速發展，智慧城市服務逐漸由單一系統建置轉向平台化與整合式服務。然而，生成式人工智慧一站式賦能平台在推動過程中，常需同時整合多雲基礎資源、模型服務、資料處理、API 串接、應用模組與維運支援，使成本結構呈現高度複雜與動態變化。若平台服務提供者缺乏清楚的成本治理與報價邏輯，將不易掌握實際成本與毛利，也可能影響客戶對方案價值、預算與導入效益之判斷。 本研究以某企業智慧城市事業單位之生成式人工智慧一站式賦能平台為個案，採用質性個案研究法，並輔以主要公有雲服務供應商之虛擬機器公開定價資料進行多雲成本比較。研究目的在於探討平台服務提供者如何在多雲、多模型與多服務疊加之情境下，建立可被理解、可被追蹤且可持續調整之定價管理機制。本研究結合成本治理、分層訂閱、參數化定價與敏捷檢視與調適精神，提出「成本治理導向之敏捷分層定價框架」。 研究結果顯示，生成式人工智慧平台之定價問題並非單純制定價格表，而是一項連結成本可視性、方案價值表達、報價參數與滾動檢討之持續性管理活動。本研究將平台成本區分為基礎雲端層、模型服務層、應用整合層與治理支援層，並提出基礎導入型、進階應用型與治理整合型三種方案情境，使複雜平台服務得以轉化為客戶較易理解之方案結構。同時，本研究以 Billing Cycle 作為定價衝刺週期，使平台價格能依據成本、用量與客戶回饋進行滾動調整。整體而言，本研究可作為生成式人工智慧平台服務提供者進行成本治理、分層訂閱設計與動態定價管理之參考。;With the rapid development of generative artificial intelligence， smart city services are gradually shifting from single-system implementation toward platform-based and integrated services. However， in the process of promoting a generative AI one-stop enablement platform， service providers often need to integrate multi-cloud infrastructure， model services， data processing， API connections， application modules， and operation and maintenance support. As a result， the cost structure becomes highly complex and dynamic. Without clear cost governance and pricing logic， platform service providers may find it difficult to control actual costs and profit margins， and customers may also face difficulties in evaluating service value， budget requirements， and implementation benefits. This study takes the generative AI one-stop enablement platform of a smart city business unit in a company as the research case. A qualitative case study approach is adopted， supplemented by a comparison of public virtual machine pricing data from major public cloud service providers. The purpose of this study is to explore how platform service providers can establish a pricing management mechanism that is understandable， traceable， and continuously adjustable under the context of multi-cloud， multi-model， and multi-service integration. By integrating cost governance， tiered subscription， parametric pricing， and agile inspect-and-adapt concepts， this study proposes a Cost-Governed Agile Tiered Pricing Framework. The findings indicate that pricing for generative AI platforms is not merely about setting a price list， but rather a continuous management activity that connects cost visibility， value communication， pricing parameters， and rolling review mechanisms. This study classifies platform costs into four layers: cloud infrastructure， model services， application integration， and governance support. It also proposes three service scenarios: basic adoption， advanced application， and governance integration， thereby transforming complex platform services into a more understandable tiered structure for customers. In addition， this study uses the Billing Cycle as a pricing sprint cycle， enabling platform prices to be adjusted continuously based on costs， usage， and customer feedback. Overall， this study provides a reference for generative AI platform service providers in cost governance， tiered subscription design， and dynamic pricing management.
