by NVIDIA
NVIDIA open-source model router that selects a suitable LLM for each task to reduce cost.
Updated EU status checked Last shown
Sources: creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
NeMo Switchyard is an NVIDIA library, described as an open-source model router. It sends each request to a model chosen for the task instead of using a single model for everything.
According to a YouTube creator (AI Search), a setup combining Opus 4.8 with other models completed more tasks at about three times lower cost than using Opus 4.8 alone. This is a second-hand claim and has not been verified against official documentation.
No official page, repository, license or release details could be retrieved, so supported routing strategies, model providers, installation method and licensing are not confirmed here.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Open-source model router that picks the best model per task. With Opus 4.8 and other models it completed more tasks at about three times lower cost than Opus 4.8 alone.
Closest neighbours by meaning, not just by category.
Model · NVIDIA
NVIDIA's open-weight 30B mixture-of-experts model with 1M-token context, aimed at long-running agent workloads.
Model · NVIDIA
NVIDIA's open-weight ~550B mixture-of-experts LLM with a hybrid Mamba-transformer design, aimed at agentic workloads.
Model · Nvidia
NVIDIA's family of open models for agentic AI: reasoning, vision, speech, retrieval and safety models.
Model · NVIDIA
NVIDIA's open multimodal model (120B total, 12B active parameters) for image, video and document understanding.
Model · Unbiased
Routing system from Unbiased that dispatches requests across several models with a checking harness; stealth name Union Alpha.
App · Ollama
Runs open AI models locally on macOS, Windows and Linux, with an optional paid cloud service for larger models.