Nvidia moves into hot market for model routers

Nvidia has launched NeMo Switchyard, a library for model routing that directs AI prompts to the most appropriate model to cut costs and improve accuracy. The move comes as Cloudflare introduced a model router and Stripe is in talks to buy OpenRouter, signaling growing interest in the technology.

Model routing has emerged as a way to keep AI inferencing costs down https://www.infoworld.com/article/4191199/model-routing-a-better-way-to-control-ai-costs.html by examining prompts and directing them to the most appropriate model — for example, the cheapest one able to respond effectively. This means that requests can be handled more efficiently, giving more accurate results and lower runtime costs, a concern in an era of rising AI expenditure https://www.arnnet.com.au/article/4173416/global-ai-spend-to-hit-us2-59t-in-2026-gartner.html . Nvidia sees the potential for model routing and has just launched NeMo Switchyard https://developer.nvidia.com/blog/route-ai-agent-workloads-across-models-with-nvidia-nemo-switchyard , its take on the technology. Switchyard provides a library for applying multiple routing approaches, enabling developers to apply a system-of-models https://www.nvidia.com/en-us/glossary/multi-agent-systems/ :~:text=request%20is%20inputted.-,System%20of%20Models,-Depending%20on%20the approach and build more efficient, controllable agents. Interest in model routing is growing — both as a tool and as an investment: Cloudflare recently introduced a model router https://www.cio.com/article/4206332/cloudflare-wants-to-provide-the-operating-system-for-the-ai-first-enterprise.html as part of a new suite of enterprise AI tools, while payment services company Stripe is looking to buy OpenRouter, according to The Wall Street Journal https://www.wsj.com/tech/ai/stripe-in-talks-to-buy-buzzy-ai-model-marketplace-openrouter-decc6a74 . Companies will certainly be looking at routing options more carefully in the future as they work out how best to marry their infrastructures with their AI demands. This article first appeared on InfoWorld.