NVIDIA · all models ›

NSwitchyardOPEN

Switchyard is an open-source model routing system that switches between multiple models to optimize the cost of requests.

1MContext window · tokens
FreeInput price · per M tokens
FreeOutput price · per M tokens
NVIDIAProvider

Prices update automatically — checked daily against provider list prices.

See model comparisons → Compare all model prices

Benchmarks

Artificial Analysis measures 51 of the 426 models tracked here — this one is not yet covered. The pricing position above is measured across the full catalog and does not depend on benchmarks.

About this model

Switchyard is an open-weight AI model by NVIDIA. You can download and self-host it for free; the prices below are hosted-API list prices, tracked daily, for when you prefer convenience over self-hosting.

Frequently asked questions

What is Switchyard?

Switchyard is an AI language model from NVIDIA. It is open-weight: you can download it and run it on your own hardware, for free.

Is Switchyard free?

The weights are free and open — you can self-host Switchyard and pay nothing per token. If you prefer a hosted API, list prices are Free per million input tokens and Free per million output tokens.

Can I self-host Switchyard?

Yes. Switchyard has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.

Related models

Nemotron 3 Ultra (free)NVIDIANemotron 3.5 Super VL (free)NVIDIANemotron 3.5 Lightning (free)NVIDIANemotron 3.5 Super VLNVIDIANemotron 3 UltraNVIDIANemotron 3 Nano Omni (free)NVIDIA