SoftwareFramework

LLMRouter

Project record

Maintained by U Lab, University of Illinois Urbana-Champaign1 2 5

LLMRouter is an open-source Python library for routing each query to a suitable large language model, balancing response quality against inference cost. It implements more than 16 routing methods across single-round, multi-round, multimodal, agentic, and personalized routers, and adds a command-line interface, a Gradio chat interface, and a pipeline for generating routing training data. The accompanying paper introduces xRouteBench, a routing benchmark.1 4Fact reviewed Oct 1, 2026

Repository: Repository (ulab-uiuc/LLMRouter) (external site: github.com)
Documentation: Project page and documentation (external site: ulab-uiuc.github.io)
Paper: Paper: LLMRouter (arXiv 2608.06867) (external site: arxiv.org)
License: LICENSE (MIT) (external site: github.com)

Last reviewedOct 1, 2026Entry updated Oct 1, 2026Documented release Unknown

Availability and license

Overall availability

Public

Source code is public on GitHub, and the package is installable from PyPI as llmrouter-lib. Running inference, chat, or data generation requires API keys for the LLM services being routed.1

Availability fact review: Oct 1, 2026

Availability is separate from permission: read the license before using or redistributing.

MIT License (external site: github.com)2
Applies to: Code · SPDX MIT · on the rubric’s OSI-approved software-license list · fact reviewed Oct 1, 2026

Component reuse rights

A readable or downloadable component is not automatically reusable. These indicators concern recorded license evidence, not system certification.

weights: Unknown — no complete fact-level rights review
code: Reviewed qualifying license recorded — check scope and conditions
data: Unknown — no complete fact-level rights review
documentation: Unknown — no complete fact-level rights review

No complete system-rights review is recorded for this release.

Public materials checklist

Items for a framework under USASI rubric v0.2. Unknown means unassessed or insufficient evidence.

Public materials checklist for LLMRouter
Item	Status	Notes and evidence
Source codeIs the source code publicly readable?	Public	Public GitHub repository under the MIT License.1 2
DocumentationIs user documentation published?	Public	The README covers installation, API key setup, and command-line usage; a project page links the paper, tutorials, a blog, and a leaderboard.1 3
InstallationAre installation instructions or packages publicly available?	Public	Install from source in a Python 3.10 environment with "pip install -e ." (with optional extras), or from PyPI with "pip install llmrouter-lib".1
Supported platformsAre supported operating systems or hardware documented?	Partial	The README's setup uses Python 3.10 and says the optional Router-R1 extra requires a GPU and is tested with vLLM 0.6.3 and PyTorch 2.4.0. No operating-system support list was found.1
Release statusAre versioned releases published?	Partial	The GitHub repository has no release entries. The README's news items mention PyPI package versions llmrouter-lib v0.2.0 (January 2026) and v0.3.1 (February 2026).1

What it is useful for

Training, evaluating, and deploying LLM routers that choose among candidate models from one or more API providers, and comparing routing methods under a shared quality and cost objective. The README also describes an OpenAI-compatible router server.1 3Fact reviewed Oct 1, 2026

Run and use notes

Documented facts only. No hardware or performance claims are made without a cited source and stated assumptions.

The README states that LLMRouter needs API keys, set through an API_KEYS environment variable, to call LLM endpoints for inference, chat, and data generation; keys can be grouped by service provider.1

Organization context

University of Illinois Urbana-Champaign

U.S. eligibility

Project eligibility rests on documented governing or maintaining entities, not on contributors.

Eligible · basis: U.S.-governed project

LLMRouter is maintained in the GitHub organization of U Lab at the University of Illinois Urbana-Champaign, and its MIT License names U Lab @UIUC as copyright holder. The project page lists authors from UIUC together with collaborators from the University of Maryland, Nanyang Technological University, Purdue University, and the University of Illinois Chicago; eligibility rests on the maintaining lab, not on authorship.1 2 5 3

Assessed Oct 1, 2026

Sources

1.
ulab-uiuc/LLMRouter (GitHub repository and README) (external site: github.com)
U Lab, University of Illinois Urbana-Champaign · Repository · accessed Oct 1, 2026 · evidence reviewed Oct 1, 2026
2.
LLMRouter LICENSE (MIT License) (external site: raw.githubusercontent.com)
U Lab @UIUC · License · accessed Oct 1, 2026 · evidence reviewed Oct 1, 2026
3.
LLMRouter project page (external site: ulab-uiuc.github.io)
U Lab, University of Illinois Urbana-Champaign · Documentation · accessed Oct 1, 2026 · evidence reviewed Oct 1, 2026
4.
LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers (arXiv 2608.06867) (external site: arxiv.org)
arXiv (U Lab and co-authors) · Paper · published Aug 7, 2026 · accessed Oct 1, 2026 · evidence reviewed Oct 1, 2026
5.
U Lab @UIUC (GitHub organization) (external site: github.com)
U Lab, University of Illinois Urbana-Champaign · Repository · accessed Oct 1, 2026 · evidence reviewed Oct 1, 2026

Email a correction Report a correction Edit this entry

This listing is not an endorsement, a safety assessment, or a federal approval.