Runway Model Routers — model skill for tools & renderers

For AI agents: find the right skill in one call — curl -s "https://skills.varg.ai/api/search?q=<what the person wants>" returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the use-case page.

Send generation through a saved Runway Model Router config instead of hard-coding one model.

What it does

Routes an application's image, video or audio generation through a saved Runway Model Router configuration, and inspects or manages routers on request. It resolves the live config and current router docs, and explains why a routed request landed on a given model.

Use when

Not for

Install

Example output

https://skills.varg.ai/previews/runway-dev-model-routers.mp4 — Output picked by a quality-optimized Model Router with a $1 cap (routed to Gemini Omni Flash 1.0) for the 'OPEN awning' image-to-video prompt in Runway's router evaluation post (credit: Runway, https://runway.com/news/developers/evaluating-runway-model-router)

More tools & renderers skills

Run the generation on varg

varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.