Use the Runway API via direct curl calls to generate AI videos from images, text, or video inputs.

Official docs: https://docs.dev.runwayml.com/

Use this skill when you need to:

• Generate video from images (image-to-video)
• Generate video from text prompts (text-to-video)
• Transform existing videos (video-to-video)
• Generate images from text (text-to-image)
• Upscale video resolution (4X upscale)
• Generate sound effects or speech

1. Sign up at Runway Developer Portal
2. Purchase credits ($10 for 1000 credits)
3. Create an API key in the dashboard
4. Store it in the environment variable RUNWAY_API_KEY

export RUNWAY_API_KEY="your-api-key"

• Credits are consumed per generation
• ~25 credits per 5-second video

Important: When using $VAR in a command that pipes to another command, wrap the command containing $VAR in bash -c '...'. Due to a Claude Code bug, environment variables are silently cleared when pipes are used directly.

bash -c 'curl -s "https://api.example.com" -H "Authorization: Bearer $API_KEY"'

All examples below assume you have RUNWAY_API_KEY set.

Base URL: https://api.dev.runwayml.com/v1

Required headers for all requests:

• Authorization: Bearer ${RUNWAY_API_KEY}
• X-Runway-Version: 2024-11-06
• Content-Type: application/json

Check your credit balance:

bash -c 'curl -s -X GET "https://api.dev.runwayml.com/v1/organization" --header "Authorization: Bearer ${RUNWAY_API_KEY}" --header "X-Runway-Version: 2024-11-06"'

Generate a video from an image:

Write to /tmp/runway_request.json:

{
  "model": "gen4_turbo",
  "promptImage": "https://example.com/your-image.jpg",
  "promptText": "A timelapse of clouds moving across the sky",
  "ratio": "1280:720",
  "duration": 5
}

Then run:

bash -c 'curl -s -X POST "https://api.dev.runwayml.com/v1/image_to_video" --header "Authorization: Bearer ${RUNWAY_API_KEY}" --header "X-Runway-Version: 2024-11-06" --header "Content-Type: application/json" -d @/tmp/runway_request.json'

Response:

{
  "id": "task-id-here"
}

Generate a video from text only:

Note: Text-to-video only supports duration values of 4, 6, or 8 seconds (not arbitrary values like image-to-video).

Write to /tmp/runway_request.json:

{
  "model": "veo3.1",
  "promptText": "A serene forest with sunlight filtering through the trees",
  "ratio": "1280:720",
  "duration": 6
}

Then run:

bash -c 'curl -s -X POST "https://api.dev.runwayml.com/v1/text_to_video" --header "Authorization: Bearer ${RUNWAY_API_KEY}" --header "X-Runway-Version: 2024-11-06" --header "Content-Type: application/json" -d @/tmp/runway_request.json'

Transform an existing video:

Write to /tmp/runway_request.json:

{
  "model": "gen4_aleph",
  "videoUri": "https://example.com/source-video.mp4",
  "promptText": "Add magical sparkles and fairy dust effects",
  "ratio": "1280:720"
}

Then run:

bash -c 'curl -s -X POST "https://api.dev.runwayml.com/v1/video_to_video" --header "Authorization: Bearer ${RUNWAY_API_KEY}" --header "X-Runway-Version: 2024-11-06" --header "Content-Type: application/json" -d @/tmp/runway_request.json'

Generate images from text:

Write to /tmp/runway_request.json:

{
  "model": "gen4_image_turbo",
  "promptText": "A futuristic cityscape at sunset",
  "ratio": "1920:1080",
  "referenceImages": []
}

Then run:

bash -c 'curl -s -X POST "https://api.dev.runwayml.com/v1/text_to_image" --header "Authorization: Bearer ${RUNWAY_API_KEY}" --header "X-Runway-Version: 2024-11-06" --header "Content-Type: application/json" -d @/tmp/runway_request.json'

Poll for task completion. Replace <your-task-id> with the actual task ID:

bash -c 'curl -s -X GET "https://api.dev.runwayml.com/v1/tasks/<your-task-id>" --header "Authorization: Bearer ${RUNWAY_API_KEY}" --header "X-Runway-Version: 2024-11-06"'

Response when complete:

{
  "id": "task-id",
  "status": "SUCCEEDED",
  "output": ["https://cdn.runwayml.com/generated-video.mp4"]
}

Possible statuses: PENDING, RUNNING, SUCCEEDED, FAILED

Cancel a running task. Replace <your-task-id> with the actual task ID:

bash -c 'curl -s -X DELETE "https://api.dev.runwayml.com/v1/tasks/<your-task-id>" --header "Authorization: Bearer ${RUNWAY_API_KEY}" --header "X-Runway-Version: 2024-11-06"'

Upscale video resolution:

Write to /tmp/runway_request.json:

{
  "model": "upscale_v1",
  "videoUri": "https://example.com/low-res-video.mp4"
}

Then run:

bash -c 'curl -s -X POST "https://api.dev.runwayml.com/v1/video_upscale" --header "Authorization: Bearer ${RUNWAY_API_KEY}" --header "X-Runway-Version: 2024-11-06" --header "Content-Type: application/json" -d @/tmp/runway_request.json'

Generate audio from text:

Write to /tmp/runway_request.json:

{
  "model": "eleven_text_to_sound_v2",
  "promptText": "Thunder rumbling in the distance"
}

Then run:

bash -c 'curl -s -X POST "https://api.dev.runwayml.com/v1/sound_effect" --header "Authorization: Bearer ${RUNWAY_API_KEY}" --header "X-Runway-Version: 2024-11-06" --header "Content-Type: application/json" -d @/tmp/runway_request.json'

Common ratios for video generation:

• 1280:720 (16:9 landscape)
• 720:1280 (9:16 portrait)
• 1024:1024 (1:1 square)

1. Poll for completion: Video generation is async; poll /tasks/{id} until status is SUCCEEDED
2. Use appropriate models: gen4_turbo is faster, gen4_aleph for video-to-video
3. Download promptly: Output URLs may expire after some time
4. Monitor credits: Check /organization endpoint to track usage
5. Handle rate limits: API returns 429 when rate limited; add delays