laya_router: a model router with Laya matches GPT-5 nano's accuracy, 35x faster, free
Two LLM routers behind one endpoint compared on 180 labelled requests: Laya picks small, medium or powerful in one forward pass versus a GPT-5 nano reasoning router. Local and free for the Laya side.

- Launch
- Laya
- Use case
- Research
- Format
- Repo
- Source
- github.com
Gleb Lukicov
Lead MLOps Engineer | PhD in Physics



