LLMRouter

Hi HN, We are a CS research team from UIUC. We just open-sourced LLMRouter, a unified library for LLM routing across different settings. The motivation came from our own research and engineering work. Over the past year, we built and benchmarked multiple LLM routing systems, including GraphRouter (ICLR’25), Router-R1 (NeurIPS’25), and PersonalizedRouter (TMLR’25). What we consistently ran into was not an algorithmic issue, but an infrastructure one. Today, most LLM routers come with custom input/output formats, training pipelines, and evaluation setups. This makes routers hard to reuse, hard to compare, and costly to integrate into real systems. LLMRouter aims to standardize this layer. It provides: Unified support for single-round, multi-round, agentic, and personalized routing Implementations of 16+ state-of-the-art LLM routing algorith

OP here. I'm a CS PhD student at UIUC working on User Modeling and Applied ML. We built LLMRouter because we noticed a gap in the current LLM stack: everyone knows we shouldn't route every query to GPT-4/o1 (it's slow and expensive), but building a reliable router that handles context, reasoning, and user history is surprisingly hard. Most existing solutions are either simple regex/keyword matching or closed-source APIs. We wanted to build a standard, open-source library that unifies the SOTA. What LLMRouter actually does: It provides a unified interface to 16+ routing strategies, ranging from lightweight ML to heavy reasoning agents: Single-Round: Classification-based (KNN, SVM, BERT) and Embedding-based methods. Multi-Round & Agentic: Routers that "think" before assigning models (CoT reasoning) or break down tasks step-by-step. Personal