---
name: runway
description: Operate Runway as an agent using public APIs, CLIs, and docs. Twin Score agent 64.
---

# Runway skill

Runway builds generative video tools (Gen-3 and successors) used by filmmakers, marketers, and motion teams. The web studio is the human product: timeline, motion brush, lip sync, and generating clips from text or images. An API exists for generating assets in pipelines, which lifts the agent score above Discord-only tools, but video jobs are asynchronous, expensive, and less deterministic than a JSON chat API. Twin Score on this directory is 81 for humans and 64 for agents, using the public rubric (interface, onboarding, human docs, collaboration, support, pricing fairness, accessibility, reliability versus API quality, MCP or tool surface, CLI, structured docs, machine auth, quotas, determinism, and skill packaging). Runway is sold by Runway ML, founded 2018, headquartered in New York, USA. Pricing in public materials: Free trial credits; Standard, Pro, and Unlimited plans with credit or seat billing. Machine capabilities we record: API strong, MCP none, CLI none, docs strong, auth Account and API tokens. This page is editorial, not a star rating scraped from users.

## When to use

Use this skill when a user asks to integrate, script, or evaluate Runway (Runway ML).

## When not to use

Do not claim an MCP server exists unless the capability matrix says so (current MCP level: none). Do not invent user-count ratings.

## Capability matrix

| Surface | Level |
|---|---|
| API | strong |
| MCP | none |
| CLI | none |
| Docs | strong |
| Auth | Account and API tokens |
| Webhooks | strong |
| SDKs | http |

## Auth

Account and API tokens

## Pricing (public)

Free trial credits; Standard, Pro, and Unlimited plans with credit or seat billing.

## Official site

https://runwayml.com

## Twin Score

Human 81. Agent 64. Updated 2026-08-01. Rubric: https://buildsomethingagentswant.com/scorecard

## Alternatives

- midjourney
- adobe-firefly
- canva