thu-nics/R2R

[NeurIPS'26] The official code implementation for paper "TokenRouter: Efficient Serving System for Token-Level LLM Routing"

Efficient LLM query routing via multi-sampling. BEST-Route selects both model and number of responses based on query difficulty, cutting costs by up to 60% with <1% performance drop. From the paper:https://arxiv.org/abs/2506.22716

A curated list of awesome works in Routing LLMs paradigm (👉 Welcome to submit your contributions to this code repository)

LLMRouter: An Open-Source Library for LLM Routing

A tiny ~10K-parameter LLM router that learns which open-source model (deepseek-v4-pro / glm-5p2 / kimi-k2p6 via Fireworks) should answer each question and in what role, trained by evolution (sep-CMA-ES).

The code for the paper ROUTERBENCH: A Benchmark for Multi-LLM Routing System

[NeurIPS 2025 Spotlight] LLM post-training suite — featuring ReasonFlux, ReasonFlux-PRM, and ReasonFlux-Coder.

A framework for serving and evaluating LLM routers - save LLM costs without compromising quality

An open, programmable decision layer for models and compute.