[{"data":1,"prerenderedAt":4},["ShallowReactive",2],{"readme:llmrouter":3},"\u003Cdiv align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fulab-uiuc\u002Fllmrouter\u002FHEAD\u002Fassets\u002Flogo_claw.png\" alt=\"LLMRouter Logo\" width=\"200\" \u002F>\n\u003C\u002Fdiv>\u003Ch1>🚀 LLMRouter: An Open-Source Library for LLM Routing\u003C\u002Fh1>\u003Cdiv align=\"center\">\n  \u003Cp>\n    \u003Ca href=\"https:\u002F\u002Fwww.python.org\u002Fdownloads\u002Frelease\u002Fpython-3109\u002F\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPYTHON-3.10-3776AB?style=for-the-badge&logo=python&logoColor=white\" alt=\"Python\" \u002F>\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fulab-uiuc\u002FLLMRouter\u002Fpulls\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPRS-WELCOME-orange?style=for-the-badge\" alt=\"PRs\" \u002F>\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fjoin.slack.com\u002Ft\u002Fllmrouteropen-ri04588\u002Fshared_invite\u002Fzt-3mkx82cut-A25v5yR52xVKi7_jm_YK_w\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FSLACK-JOIN%20US-4A154B?style=for-the-badge&logo=slack&logoColor=white\" alt=\"Slack\" \u002F>\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fulab-uiuc\u002FLLMRouter\u002Fissues\u002F136\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F💬WeChat-Group-07c160?style=for-the-badge&logo=wechat&logoColor=white&labelColor=1a1a2e\" alt=\"WeChat\" \u002F>\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fulab-uiuc.github.io\u002FLLMRouter\u002F\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDOCS-ONLINE-0A9EDC?style=for-the-badge&logo=readthedocs&logoColor=white\" alt=\"Docs\" \u002F>\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2608.06867\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPAPER-B31B1B?style=for-the-badge&logo=arxiv&logoColor=white\" alt=\"Paper\" \u002F>\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fx.com\u002Fyoujiaxuan\u002Fstatus\u002F2005877938554589370\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FTWITTER-ANNOUNCEMENTS-1DA1F2?style=for-the-badge&logo=x&logoColor=white\" alt=\"Twitter\" \u002F>\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002Fulab-ai\u002FxRouteBench\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fulab-uiuc\u002Fllmrouter\u002FHEAD\u002Fassets\u002Fhf-logo.svg\" alt=\"xRouteBench\" height=\"28\" \u002F>\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FHUGGING%20FACE-xRouteBench-FFD21E?style=for-the-badge&labelColor=555555\" alt=\"xRouteBench Dataset\" height=\"28\" \u002F>\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fulab-uiuc\u002Fllmrouter\u002Fblob\u002FHEAD\u002FLICENSE\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLICENSE-MIT-2EA44F?style=for-the-badge\" alt=\"License\" \u002F>\u003C\u002Fa>\n  \u003C\u002Fp>\n\u003C\u002Fdiv>\u003Ch2>✨ Introduction\u003C\u002Fh2>\n\u003Cdiv align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fulab-uiuc\u002Fllmrouter\u002FHEAD\u002Fassets\u002Fllmrouter_.png\" alt=\"LLMRouter Overview\" \u002F>\n\u003C\u002Fdiv>\u003Cp>\u003Cstrong>LLMRouter\u003C\u002Fstrong> is an intelligent routing system designed to optimize LLM inference by dynamically selecting the most suitable model for each query. To achieve intelligent routing, it defines:\u003C\u002Fp>\n\u003Col>\n\u003Cli>🚀 \u003Cem>Smart Routing\u003C\u002Fem>: Automatically routes queries to the optimal LLM based on task complexity, cost, and performance requirements.\u003C\u002Fli>\n\u003Cli>📊 \u003Cem>Multiple Router Models\u003C\u002Fem>: Support for \u003Cstrong>over 16 routing models\u003C\u002Fstrong>, organized into five major categories—\u003Cstrong>single-round routers, multi-round routers, multimodal routers, agentic routers, and personalized routers\u003C\u002Fstrong>—covering a wide range of strategies such as KNN, SVM, MLP, Matrix Factorization, Elo Rating, graph-based routing, BERT-based routing, hybrid probabilistic methods, transformed-score routers, and more.\u003C\u002Fli>\n\u003Cli>🛠️ \u003Cem>Unified CLI\u003C\u002Fem>: Complete command-line interface for training, inference, and interactive chat with Gradio-based UI.\u003C\u002Fli>\n\u003Cli>📈 \u003Cem>Data Generation Pipeline\u003C\u002Fem>: Complete pipeline for generating training data from 11 benchmark datasets with automatic API calling and evaluation.\u003C\u002Fli>\n\u003C\u002Fol>\n\u003Ch2>📰 News\u003C\u002Fh2>\n\u003Cul>\n\u003Cli>\u003Cp>🔥 \u003Cstrong>[2026-08]\u003C\u002Fstrong>: We are honored to have \u003Cstrong>LLMRouter\u003C\u002Fstrong> featured among the top papers on 🤗 Hugging Face \u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fpapers\u002F2608.06867\" rel=\"nofollow ugc noopener\">Daily Papers\u003C\u002Fa>.\u003C\u002Fp>\n\u003C\u002Fli>\n\u003Cli>\u003Cp>🚀 \u003Cstrong>[2026-08]: LLMRouter\u003C\u002Fstrong> - We've released LLMRouter, a unified infrastructure for developing, evaluating, and deploying LLM routers! LLMRouter formulates routing as a unified sequential decision process spanning single-turn, multi-turn, and personalized scenarios, and provides a modular framework with 16+ representative routing methods. It also introduces xRouteBench, a comprehensive benchmark covering generic LLM, memory-augmented, vision, time-series, and personalized routing, with automated supervision construction and joint evaluation of response quality and inference cost. Experiments show that learned routers outperform the strongest fixed-model baseline by 14.6% relatively, wh\u003C\u002Fp>\n\u003C\u002Fli>\n\u003C\u002Ful>\n",1788652555709]