Wan 3.0 Prime Video

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

Alibaba's Wan 3.0 Prime text-to-video model. Generates cinematic videos from text prompts with adaptive aspect ratio, 480P, 720P, or 1080P resolution, and configurable duration.

Model Info
Terms and License	link ↗
More information	link ↗
Pricing	Default (per second)$0.068 @480p (per second)$0.068 @720p (per second)$0.14 @1080p (per second)$0.28

Usage

const response = await env.AI.run(
  'alibaba/wan-3.0-prime',
  {
    prompt:
      'A kitten running across a rooftop under the moonlight, city neon lights flickering in the distance, cinematic quality, smooth camera movement.',
    resolution: '480P',
    ratio: 'adaptive',
    duration: 5,
  },
)
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": "alibaba/wan-3.0-prime",
  "input": {
    "prompt": "A kitten running across a rooftop under the moonlight, city neon lights flickering in the distance, cinematic quality, smooth camera movement.",
    "resolution": "480P",
    "ratio": "adaptive",
    "duration": 5
  }
}'

{
  "state": "Completed",
  "result": {
    "video": "https://examples.aig.cloudflare.com/alibaba/wan-3.0-prime/adaptive-480p-text-to-video.mp4"
  },
  "gatewayMetadata": {
    "keySource": "Unified"
  }
}

Parameters

prompt

stringrequiredminLength: 1maxLength: 2500

resolution

stringenum: 480P, 720P, 1080P

ratio

stringenum: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4

duration

integerminimum: 1maximum: 15

video

stringformat: uri

API Schemas (Raw)

Input

Output