Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
Switchyard - Model - OpenSmartRoute
Modelv1.0.0
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...
Reference model card from the OpenRouter listing - model nvidia/switchyard. Prices are per million tokens as listed; ratings and installs below are from this marketplace.
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...
Facts
Vendor
NVIDIA
Context window
1,000,000 tokens
Input
text
Output
text
Tool calling
no
Structured outputs
no
Reasoning
no
Open weights
no
Endpoint: https://openrouter.ai/api/v1 (OpenAI-compatible), model nvidia/switchyard
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - nothing else to configurecurl-s-X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'# or pin it on the OpenAI-compatible endpoint: {"model": "model-nvidia-switchyard", ...}
Installed into a catalogue, chosen by a router
Install Switchyard and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.
When a provider is down or over quota the request moves on; the trace says it did.
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
model-nvidia-switchyard.ocm.jsonjson
{
"ocm": "1",
"id": "model-nvidia-switchyard",
"kind": "llm",
"name": "Switchyard",
"description": "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...",
"publisher": "NVIDIA",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding"
],
"tags": [
"llm",
"nvidia",
"openrouter",
"models"
],
"languages": [
"en"
],
"modalities": [
"text"
],
"supports_tools": false,
"supports_streaming": true,
"context_window": 1000000
},
"quality_prior": 0.6,
"examples": [
"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..."
],
"primary": false,
"metadata": {
"source": {
"provider": "models",
"ref": "1790025947",
"url": "https://openrouter.ai/nvidia/switchyard",
"key": "nvidia/switchyard",
"catalogue": "https://openrouter.ai/api/v1"
},
"model": "nvidia/switchyard",
"pricing": {},
"output_modalities": [
"text"
],
"created": 1790025947
},
"endpoints": [
{
"protocol": "openai",
"url": "https://openrouter.ai/api/v1"
}
]
}
Fetch it by URL: GET /api/v1/registry/model-nvidia-switchyard/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.
