Video · Runway

Runway

Video generation and editing — create and transform footage with text prompts.

Operational · 2 endpoints · à partir de $0.120
# Works with Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents
npx skills add runapi-ai/runway -g
The -g flag installs globally so every project picks it up.
Or paste this prompt to your AI agent:
Install the Runway skill for me:

1. Clone https://github.com/runapi-ai/runway
2. Copy the skills/runway/ directory into your
   user-level skills directory (e.g. ~/.claude/skills/
   for Claude Code, ~/.codex/skills/ for Codex).
3. Verify that SKILL.md is present.
4. Confirm the install path when done.
APERÇU

Runway is a professional-grade AI video generation platform supporting text-to-video and image-to-video creation. It is widely used in creative and film production workflows for generating cinematic footage.

  • Installable agent skill
  • Unified API key
  • SDK examples included
  • Les générations échouées ne sont pas facturées
TARIFS

TARIFS

Les générations échouées ne sont pas facturées
Text to video
$0.12-$0.30 / video
Duration seconds: 5 · Output resolution: 720p $0.12
Duration seconds: 5 · Output resolution: 1080p $0.30
Duration seconds: 10 · Output resolution: 720p $0.30
Extend video
$0.12-$0.30 / video
Output resolution: 720p $0.12
Output resolution: 1080p $0.30
FICHE TECHNIQUE

FICHE TECHNIQUE

Model ID runway
Fournisseur Runway
Modalité video
Task type asynchronous
Facturation call
Endpoint /api/v1/runway/extend_video
Commercial Yes
Status Operational
AGENT USAGE

Use this model from your agent

Prompt + SDK example
# User prompt to the agent
"Generate a 5-second cinematic shot of rain falling on a neon-lit Tokyo street at night."
// Code generated by the agent via @runapi.ai/runway
import { RunwayClient } from '@runapi.ai/runway';

const client = new RunwayClient();
const result = await client.extendVideo.run({
  model: 'runway',
  prompt: 'Generate a 5-second cinematic shot of rain falling on a neon-lit Tokyo street at night.',
});
@runapi.ai/runway npm
FONCTIONNEMENT

How to call this model

01

Install the skill

Add the model skill to your agent or install the SDK package.

02

Authenticate once

Use your RunAPI key for every supported model.

03

Send a request

Use the unified schema for the endpoint you need.

04

Receive output

Poll by task ID or handle the callback when the generation completes.

SDK QUICKSTART

SDK quickstart

runapi.ai
curl -X POST https://runapi.ai/api/v1/runway/extend_video \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "runway",
  "task_id": "task_abc123"
}'
import { RunwayClient } from "@runapi.ai/runway";

const client = new RunwayClient();
const result = await client.extendVideo.run({
    model: "runway",
    task_id: "task_abc123",
});
require "runapi/runway"

client = RunApi::Runway::Client.new
result = client.extend_video.run(
    model: "runway",
    task_id: "task_abc123"
)
@runapi.ai/runway v1
CONTEXTE

Where Runway fits

Runway is a leading video AI company whose models are widely used in creative production. Through RunAPI, Runway endpoints are accessible with a single key and pay-per-call pricing.

Provider
Runway
Modality
Video
POURQUOI RUNAPI

Why use Runway through RunAPI

One API key

Use the same credentials across models and providers.

Agent-ready

Installable skills include docs and schema for tool calls.

Predictable billing

Usage-based pricing is visible before you call.

FAQ

Frequently asked questions

How do I call this model?

Use the RunAPI SDK, CLI, or REST endpoint shown on this page.

Do failed generations cost money?

Les générations échouées ne sont pas facturées

Can agents use it directly?

Yes. Install the model skill and your agent gets the docs, schema, and examples.

COMMENCER

Start building with Runway.

Endpoints
  • text_to_video
  • extend_video
Category
Fournisseur
Docs