LLMProxy: Reducing Cost to Access Large Language Models

In this paper, we make a case for a proxy for large language models which has explicit support for cost-saving optimizations. We design LLMProxy, which supports three key optimizations: model selection, context management, and caching. These optimizations present tradeoffs in terms of cost, inference time, and response quality, which applications can navigate through our high level, bidirectional interface. As a case study, we implement a WhatsApp-based Q&A service that uses LLMProxy to provide a rich set of features to the users. This service is deployed on a small scale (100+ users) leveraging the cloud; it has been operational for 15+ weeks and users have asked 1400+ questions so far. We report on the experiences of running this service as well as microbenchmark the specific benefits of the various cost-optimizations we present in this paper.