# ThriftLLM: On Cost-Effective Selection of Large Language Models for Classification Queries

arXiv: https://arxiv.org/abs/2501.04901 · HTML: https://mlsanity.com/paper/2501.04901/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jan 2025.

## Built on by (most cited first, 14 of 14)

- [Optimizing Model Selection for Compound AI Systems](https://mlsanity.com/paper/2502.14815/) (2025)
- [Causal LLM Routing: End-to-End Regret Minimization from Observational Data](https://mlsanity.com/paper/2505.16037/) (2025)
- [Failure Modes in LLM Systems: A System-Level Taxonomy for Reliable AI Applications](https://mlsanity.com/paper/2511.19933/) (2025)
- [Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees](https://mlsanity.com/paper/2509.02896/) (2025)
- [Theoretical Foundations of Scaling Law in Familial Models](https://mlsanity.com/paper/2512.23407/) (2025)
- [WISERouter: LLM Routing with Workload Budget Constraint](https://mlsanity.com/paper/2607.23765/) (2026)
- [More Is Not Always Better: Cross-Component Interference in LLM Agent Scaffolding](https://mlsanity.com/paper/2605.05716/) (2026)
- [Online Learning with LLM Experts from Limited Feedback](https://mlsanity.com/paper/2609.05820/) (2026)
- [Policy-Governed LLM Routing with Intent Matching for Instrument Laboratories](https://mlsanity.com/paper/2604.26955/) (2026)
- [Adaptive Graph Refinement and Label Propagation with LLMs for Cost-Effective Entity Resolution](https://mlsanity.com/paper/2605.25814/) (2026)
- [Online LLM Selection via Constrained Bandits with Time-Varying Demand](https://mlsanity.com/paper/2606.17489/) (2026)
- [Can Agentic Trading Systems Pay for Their Own Intelligence?](https://mlsanity.com/paper/2607.10286/) (2026)
- [Cost-Optimal Foundation Model Deployment Portfolio for Transportation Management](https://mlsanity.com/paper/2607.13239/) (2026)
- [Opti-Q: A Constraint-Based Optimization Framework for Multi-LLM Question Planning](https://mlsanity.com/paper/2607.22621/) (2026)

## Abstract (arXiv)

In recent years, large language models (LLMs) have demonstrated remarkable capabilities in comprehending and generating natural language content, attracting widespread attention in both industry and academia. An increasing number of services offer LLMs for various tasks via APIs. Different LLMs demonstrate expertise in different domains of queries (e.g., text classification queries). Meanwhile, LLMs of different scales, complexities, and performance are priced diversely. Driven by this, several researchers are investigating strategies for selecting an ensemble of LLMs, aiming to decrease overall usage costs while enhancing performance. However, to the best of our knowledge, none of the existing works addresses the problem, how to find an LLM ensemble subject to a cost budget, which maximizes the ensemble performance with guarantees. In this paper, we formalize the performance of an ensemble of models (LLMs) using the notion of correctness probability, which we formally define. We develop an approach for aggregating responses from multiple LLMs to enhance ensemble performance. Building on this, we formulate the Optimal Ensemble Selection problem of selecting a set of LLMs subject to a cost budget that maximizes the overall correctness probability. We show that the correctness probability function is non-decreasing and non-submodular and provide evidence that the Optimal Ensemble Selection problem is likely to be NP-hard. By leveraging a submodular function that upper bounds correctness probability, we develop an algorithm called ThriftLLM and prove that it achieves an instance-dependent approximation guarantee with high probability. Our framework functions as a data processing system that selects appropriate LLM operators to deliver high-quality results under budget constraints.