Runway
Video generation and editing — create and transform footage with text prompts.
# Works with Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents
npx skills add runapi-ai/runway -g
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.
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
FICHE TECHNIQUE
| Model ID | runway |
| Fournisseur | Runway |
| Modalité | video |
| Task type | asynchronous |
| Facturation | call |
| Endpoint | /api/v1/runway/extend_video |
| Commercial | Yes |
| Status | Operational |
Use this model from your agent
# 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.',
});
How to call this model
Install the skill
Add the model skill to your agent or install the SDK package.
Authenticate once
Use your RunAPI key for every supported model.
Send a request
Use the unified schema for the endpoint you need.
Receive output
Poll by task ID or handle the callback when the generation completes.
SDK quickstart
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"
)
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.
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.
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.
Models similar to Runway
Start building with Runway.
- text_to_video
- extend_video