Switchyard is an open-source model routing system that switches between multiple models to optimize the cost of requests.
Prices update automatically — checked daily against provider list prices.
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.
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.
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.
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.
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.