Vigia

AI model · NVIDIA

NVIDIA: Switchyard available

nvidia/switchyard

Input price (per 1M tokens)variable
Output price (per 1M tokens)variable
Context window1,000,000
Max output tokens—
Announced retirement datenone
Knowledge cutoff—
Last verified2026-10-13 09:44:29 UTC

Reference prices from OpenRouter (aggregator); they may differ from the provider's direct pricing.

Frequently asked questions

How much does NVIDIA: Switchyard cost?

NVIDIA: Switchyard has variable pricing; check the provider for the current rate.

What is the context window of NVIDIA: Switchyard?

NVIDIA: Switchyard accepts up to 1,000,000 tokens of context.

Is NVIDIA: Switchyard being retired?

No retirement date has been announced for NVIDIA: Switchyard (checked 2026-10-13).

Other NVIDIA models

ModelInput / 1MOutput / 1MContext
nvidia/nemotron-3.5-lightningUS$ 0.07US$ 0.2262,144
nvidia/nemotron-3.5-lightning:freeUS$ 0US$ 01,000,000
nvidia/nemotron-3.5-content-safetyUS$ 0.2US$ 0.2131,072
nvidia/nemotron-3.5-content-safety:freeUS$ 0US$ 0128,000
nvidia/nemotron-3-ultra-550b-a55bUS$ 0.6US$ 2.40262,144
nvidia/nemotron-3-ultra-550b-a55b:freeUS$ 0US$ 01,000,000
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:freeUS$ 0US$ 0256,000
nvidia/nemotron-3-super-120b-a12bUS$ 0.08US$ 0.45262,144
nvidia/nemotron-3-super-120b-a12b:freeUS$ 0US$ 0262,144
nvidia/nemotron-3-nano-30b-a3bUS$ 0.06US$ 0.24262,144

Give your AI agent these facts

Vigia is a free MCP server: your coding agent checks versions, breaking changes and vulnerabilities before it writes code. No signup, no API key.

claude mcp add --transport http vigia https://vigia.coredls.cloud/mcp

Add to CursorAdd to VS Code★ Star on GitHub

Any other MCP client
{ "mcpServers": { "vigia": { "url": "https://vigia.coredls.cloud/mcp" } } }

Agent skill (SKILL.md): tells the agent when to use Vigia · GitHub Action for pull requests

For agents

GET https://vigia.coredls.cloud/v1/models/nvidia/switchyard