Runway Provider Guide
Image-to-video generation via Runway Gen-3 / Gen-4
Overview
Runway ships the Gen-3 and Gen-4 video models
behind a REST API. NeuroLink dispatches via output: { mode: 'video' }
with provider: "runway".
Key Facts
- Endpoint:
POST https://api.dev.runwayml.com/v1/image_to_video(production endpoint may differ — check Runway dashboard) - Auth: Bearer token
- Async: Submit + poll
- Output: MP4
Quick Start
1. Get an API Key
https://app.runwayml.com/settings/developer
2. Configure
RUNWAY_API_KEY=your-key
3. Generate a Video
import { NeuroLink } from "@juspay/neurolink";
import { readFileSync, writeFileSync } from "node:fs";
const ai = new NeuroLink();
const result = await ai.generate({
provider: "runway",
output: {
mode: "video",
video: { provider: "runway", resolution: "720p", length: 5 },
},
input: {
text: "Sci-fi establishing shot, soft golden hour light",
images: [readFileSync("./input.jpg")],
},
});
if (result.video?.data) {
writeFileSync("./output.mp4", result.video.data);
}
CLI Usage
pnpm run cli generate "Camera slowly orbits the subject" \
--image ./portrait.jpg \
--provider runway --videoOutput ./output.mp4
Configuration Reference
| Environment Variable | Required | Description |
|---|---|---|
RUNWAY_API_KEY | Yes | Runway API key |