Runway Builds the First AI Router Spanning Video, Image, and Audio

Model routing has been a staple of LLM infrastructure for a while now. You set a preference, the system picks the cheapest or fastest model that meets your bar, and you stop worrying about it. Runway just brought that same idea to generative media -- and it's the first time anyone has done it for video, image, and audio generation at once.

The problem no one wanted to solve manually

The generative media model landscape has exploded. Through Runway Dev alone, developers can already access Gen-4.5, Aleph 2.0, Seedance 2, Veo 3.1, GPT Image 2, Gemini Omni Flash, ElevenLabs audio, and more. While model routers have become increasingly common in the world of large language models, Runway says this is the first built specifically for generative media.

Most developers aren't spending the time to really understand the capabilities of each model and where they excel or differ across video, image, and audio outputs. The unique proposition Runway is bringing to the table is all of that intelligence around what the best model is for each different use case. In other words: you shouldn't have to become an expert in a dozen model release notes just to ship a product.

How the router actually works

A Model Router resolves each request in two steps. First it narrows the catalog to the models that could satisfy the request -- those that you've enabled, support the capabilities required by your request, and would stay under any price cap you've set. Then it picks the best of the remaining models according to your preference for cost, latency, or quality.

A router is a named, reusable configuration you create in the Developer Portal. It gets a stable config ID that you pass in your API calls. Your code never references a specific model -- it references a preference. Here's what that looks like in practice:

import RunwayML from '@runwayml/sdk';
const client = new RunwayML({ apiKey: process.env.RUNWAYML_API_SECRET });
// Pass your router config ID instead of a model name
const task = await client.textToVideo.create({
  routerConfigId: 'your-quality-router-id',
  promptText: 'A drone shot flying over a misty mountain range at dawn',
});
// Response tells you which model ran and what it cost
console.log(task.model, task.creditsUsed);