nvidia

NVIDIA: Switchyard

nvidia/switchyard

Switchyard is an open-source model router that switches between multiple models to optimize the cost of requests. By default it will use OpenRouter market data to select the most popular...

text

Try in Playground ↗

Input / 1M tokensVariable

Output / 1M tokensVariable

Context window1,000,000

Maximum output32,768

Provider-supported parameters

These are upstream capabilities. Jevrouter supports the subset described in the API contract; chat input is currently text only.

streammax_tokensdeveloper_role

Capabilities are imported from OpenRouter’s catalog. This does not mean every model has been independently tested by Jevrouter.

Catalog updated: 2026-10-03T22:19:24.250Z · Price version: cmurizngi1i3pj40zpfkhvo3a:1

Provider pricing fields · USD per indicated unit

{
  "prompt": "-1",
  "completion": "-1"
}

Make a request

curl --no-buffer https://api.jevrouter.io/v1/chat/completions \
  -H "Authorization: Bearer $JEVROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d @- <<'JSON'
{
  "model": "nvidia/switchyard",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "max_tokens": 1024
}
JSON

Plan your integration

Connect with the OpenAI Python SDK →Estimate this model’s cost →Budgets, request status and safe retries →

Source: OpenRouter model catalog. Imported descriptions and capabilities are provider declarations, not independent benchmark results. Jevrouter currently uses OpenRouter as its managed upstream.