Use the Runway API via RunAPI with a model skill, unified auth, and pay-as-you-go pricing.
curl -X POST https://runapi.ai/api/v1/runway/extend_video \
-H "Authorization: Bearer $RUNAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "runway",
"source_task_id": "task_abc123"
}'import { RunwayClient } from "@runapi.ai/runway";
const client = new RunwayClient();
const result = await client.extendVideo.run({
model: "runway",
source_task_id: "task_abc123",
});<?php
require __DIR__ . "/vendor/autoload.php";
use RunApi\Runway\RunwayClient;
$client = new RunwayClient();
$result = $client->extendVideo->run([
'model' => 'runway',
'source_task_id' => 'task_abc123',
]);require "runapi/runway"
client = RunApi::Runway::Client.new
result = client.extend_video.run(
model: "runway",
source_task_id: "task_abc123"
)npx skills add runapi-ai/runway -g# Claude Code
claude mcp add runapi -s user -- npx -y @runapi.ai/mcp
# Codex
codex plugin install runapi-mcp@agents
# Cursor / Windsurf / VS Code
npx @runapi.ai/mcp init cursorRunway 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.
| Model ID | runway |
| Provider | Runway |
| Modality | video |
| Task type | asynchronous |
| Billing unit | call |
| API endpoint | /api/v1/runway/extend_video |
| Commercial license | Yes — included via API |
| Catalog status | Operational |
Sign up and generate an API key from the dashboard.
Choose the version that best matches your quality and cost requirements.
Submit your prompt and parameters to the model's documented endpoint.
Poll the task or set a webhook, then download the completed output.
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.
A single RunAPI API key unlocks the whole model catalog across all providers. No separate accounts to create, no API keys to rotate per integration, and no credential management overhead. Add a new model to your app by changing one parameter.
Per-call pricing in USD, billed monthly into a single invoice. No subscription tiers, no minimum spend, and failed generations are never charged. The pricing page and check_pricing API show exact costs before you commit to a model.
Typed schemas, parameter constraints, and setup notes are packaged in the model skill so your implementation starts from the right contract. The skill loads into Claude Code, Codex, Gemini CLI, Cursor, and VS Code — your agent knows the correct request shape before you write a line of code.
5 to 10 seconds per generation. The Extend endpoint works once from a text-to-video result and cannot be chained or re-extended.
720p or 1080p, with 1080p available for 5-second clips. Outputs are optimized for widescreen creative and cinematic workflows.
Yes — both text-to-video and image-to-video are supported. Image input sets the first frame and the model animates from there.
Extend takes a text-to-video result and continues it once for additional seconds, maintaining scene consistency and motion.
Generation time depends on duration and complexity. Results are delivered via webhook callback.
Pick the cheapest variant that meets your quality bar. Most teams start on the fast variant and graduate to pro for production.