This paper explores the a re ate effect when caching multiple versions of the same Web object in the transcoding proxy. Explicitly, the aggregate pro?t from caching multiple versions of an object is not simply the sum of the pro?ts from caching individual versions, but rather, depends on the transcoding relationships among them. Hence, to evaluate the pro?t from caching each version of an object ef?ciently, we devise the notion of a weighted transcoding graph and formulate a generalized pro?t function which explicitly considers the aggregate effect and several new emerging factors in the transcoding proxy. Based on the weighted transcoding graph and the generalized pro?t function, an innovative cache replacement algorithm for transcoding proxies is proposed in this paper. Experimental results show that the algorithm proposed consistently outperforms companion schemes in terms of the delay saving ratios and cache hit ratios.