Skip to content
RunwayML logo

RunwayML Aleph 2

Text-to-Video • RunwayML

View as MarkdownAgent setup

Model ID

Use with the Workers AI binding, the AI Gateway REST API, or the Unified API.

Calling the provider directly? Use the provider's model name instead, including with provider-native endpoints or the provider's own SDK. For example, Anthropic's name for anthropic/claude-opus-4.8 is claude-opus-4-8.

  • Third-party

RunwayML's video editing model. Edit one frame to update your whole video, make changes across multiple shots, and work with up to 30 seconds of video. Supports keyframe-guided editing for precise control over specific moments in the clip.

Model Info
Terms and Licenselink ↗
More informationlink ↗
Pricing
  • Default (per second)$0.336

Usage

const response = await env.AI.run(
  'runwayml/aleph-2',
  {
    prompt: 'Transform the scene into a golden-hour sunset with warm lighting',
    video_uri: 'https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/runwayml__gen-4.5/cinematic-scene.mp4',
  },
)
console.log(response)
curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "runwayml/aleph-2",
  "input": {
    "prompt": "Transform the scene into a golden-hour sunset with warm lighting",
    "video_uri": "https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/runwayml__gen-4.5/cinematic-scene.mp4"
  }
}'
{
  "state": "Completed",
  "result": {
    "video": "https://dnznrvs05pmza.cloudfront.net/7449093b-e574-41a5-8308-05e4692fa652.mp4"
  },
  "gatewayMetadata": {
    "keySource": "Unified"
  }
}

Examples

Keyframe-Guided Edit — Edit a video using a reference image anchored to the first frame of the output
const response = await env.AI.run(
  'runwayml/aleph-2',
  {
    prompt: 'Edit the video to match the provided reference frame',
    video_uri: 'https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/runwayml__gen-4.5/nature-close-up.mp4',
    prompt_images: [
      {
        uri: 'https://upload.wikimedia.org/wikipedia/commons/8/85/Tour_Eiffel_Wikimedia_Commons_(cropped).jpg',
        position: 'first',
      },
    ],
  },
)
console.log(response)
curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "runwayml/aleph-2",
  "input": {
    "prompt": "Edit the video to match the provided reference frame",
    "video_uri": "https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/runwayml__gen-4.5/nature-close-up.mp4",
    "prompt_images": [
      {
        "uri": "https://upload.wikimedia.org/wikipedia/commons/8/85/Tour_Eiffel_Wikimedia_Commons_(cropped).jpg",
        "position": "first"
      }
    ]
  }
}'
{
  "state": "Completed",
  "result": {
    "video": "https://dnznrvs05pmza.cloudfront.net/cd7388fe-09d6-4b16-afc5-24bb315eaf14.mp4"
  },
  "gatewayMetadata": {
    "keySource": "Unified"
  }
}
Timed Keyframe Edit — Place a guidance image at a specific timestamp within the input video using keyframes[].seconds
const response = await env.AI.run(
  'runwayml/aleph-2',
  {
    prompt: 'Change the background to a futuristic cityscape at night',
    video_uri: 'https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/runwayml__gen-4.5/simple-text-to-video.mp4',
    keyframes: [
      {
        uri: 'https://upload.wikimedia.org/wikipedia/commons/8/85/Tour_Eiffel_Wikimedia_Commons_(cropped).jpg',
        seconds: 2.0,
      },
    ],
  },
)
console.log(response)
curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "runwayml/aleph-2",
  "input": {
    "prompt": "Change the background to a futuristic cityscape at night",
    "video_uri": "https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/runwayml__gen-4.5/simple-text-to-video.mp4",
    "keyframes": [
      {
        "uri": "https://upload.wikimedia.org/wikipedia/commons/8/85/Tour_Eiffel_Wikimedia_Commons_(cropped).jpg",
        "seconds": 2.0
      }
    ]
  }
}'
{
  "state": "Completed",
  "result": {
    "video": "https://dnznrvs05pmza.cloudfront.net/a7e054fa-1cf2-4265-a35c-518b8c4d6a1a.mp4"
  },
  "gatewayMetadata": {
    "keySource": "Unified"
  }
}
Content Moderation Override — Edit a video featuring public figures with relaxed content moderation
const response = await env.AI.run(
  'runwayml/aleph-2',
  {
    prompt: 'Make the background a dramatic stormy sky',
    video_uri: 'https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/runwayml__gen-4.5/cinematic-scene.mp4',
    content_moderation: {
      public_figure_threshold: 'low',
    },
  },
)
console.log(response)
curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "runwayml/aleph-2",
  "input": {
    "prompt": "Make the background a dramatic stormy sky",
    "video_uri": "https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/runwayml__gen-4.5/cinematic-scene.mp4",
    "content_moderation": {
      "public_figure_threshold": "low"
    }
  }
}'
{
  "state": "Completed",
  "result": {
    "video": "https://dnznrvs05pmza.cloudfront.net/ea5b1ccd-3dd6-43c3-86e3-5ed720849e92.mp4"
  },
  "gatewayMetadata": {
    "keySource": "Unified"
  }
}

Parameters

prompt
stringrequiredminLength: 1maxLength: 1000Text prompt describing the edit to apply to the input video
video_uri
stringrequiredHTTPS URL, Runway URI, or data URI of the source video to edit (≤30 seconds)
seed
integerminimum: 0maximum: 4294967295Random seed for reproducible results
duration
numberexclusiveMinimum: 0Duration of the source video in seconds. Used for billing only — not sent to RunwayML. Provide this so the gateway can compute per-second video cost accurately.
video
stringformat: uriURL to the edited video

API Schemas (Raw)

Input
Output

Was this helpful?