So many LLMs, each with different strengths. LLM/Model-Routing holds the promise to combine all of them and answer queries by finding the most compatible, affordable and brisk expert.
Below, we provide a curated list of research papers and studies discussing LLM routing techniques, as well as projects and companies offering LLM and model routing solutions.
Note: if a paper has both an arXiv and a conference/journal proceedings version, then we only show its proceedings version.
- Date: refers to the date of the associated publication (arXiv/proceedings).
- Affiliation: refers to the authors' company, university and/or research labs affiliations.
- Paper: provides the link to the proceedings or arXiv paper version.
- Citations: the number of citations for each paper and the published conference.
- GitHub: paper's repository.
(by alphabetic order)
| Name | Platform / App / Chat Arena | Docs | GitHub Repo |
|---|---|---|---|
| APIClaw | Platform | Docs | |
| Anyscale | Platform | Docs | GitHub |
| Aurelio AI | Course | Docs | GitHub |
| FerryAPI | Platform | Docs | |
| Langchain | Platform | Docs | GitHub |
| Martian | Platform | Docs | GitHub |
| NeutrinoAI | Platform | Docs | GitHub |
| NotDiamond | Platform | Docs | GitHub |
| Open Router | Platform | Docs | GitHub |
| Requesty | Platform | Docs | GitHub |
| Standard Compute | Platform | Docs | |
| TensorOpera | Platform | Docs | GitHub |
| Unify | Platform | Docs | GitHub |
| Weave | Weave Router | Quickstart | GitHub |
| XiuRouter | Platform | Docs |
| Name | Description | GitHub Repo |
|---|---|---|
| LLM-PQR | Provider-neutral model selection CLI using measured quality, reliability, latency, cost, capabilities, and hard privacy constraints. | GitHub |
| Bifrost | Go-native, OpenAI-compatible gateway with multi-provider routing, load balancing, and automatic failover. | GitHub |
| rust-norion | Rust-based inference control layer prototype focused on adaptive routing, memory, reflection, device/backend adaptation, benchmark gates, and auditable self-evolution workflows. | GitHub |
| ORBIT | Standardized LLM routing research and budget-aware evaluation toolbox with a common interface for routers and benchmarks. | GitHub |
| RouteFM | Pretrained, identity-free router that adapts to new candidate pools through behavioral context without retraining. | GitHub |
| RouteJudge | Public platform for reproducible, preference-aware pairwise evaluation of LLM routing systems. | GitHub |
- Hannibal046/Awesome-LLM on Large Language Models
- KennethanCeyer/awesome-llm on Large Language Models
Contributions are welcome! Please open a pull request to add or update relevant LLM-routing resources, following the existing format. If you find this list useful, consider starring and sharing the repository.
