Video Generationtextimagevideoaudio

Wan 3.0 Video Prime

阿里云万相 Wan 3.0 视频生成优速版，保持全模态统一能力并显著提升端到端生成速度。

Input

Generation mode

Describe the video with text only, no images required.

Prompt

Reference image (optional)

PNG, JPG or WebP · you can also drag and drop a file here

Duration

230

Watermark

Resolution

Aspect ratio

Generate audio

Ready to generate

API Reference

POSThttps://api.token360.ai/v1/videos

# Step 1: Create video generation task
curl https://api.token360.ai/v1/videos \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{
  "model": "wan3.0-video-prime",
  "prompt": "A cat walking across a room",
  "duration": 5,
  "watermark": false,
  "resolution": "1080p",
  "aspect_ratio": "adaptive",
  "generate_audio": true
}'

# Step 2: Poll for completion (replace VIDEO_ID with the id from step 1)
curl https://api.token360.ai/v1/videos/VIDEO_ID \
  -H "Authorization: Bearer your-api-key"

API Documentation

Overview#

Wan 3.0 Video Prime is Alibaba Cloud's faster Wan 3.0 inference service. It supports text-to-video, first/last-frame image-to-video, and reference generation from images, video, and audio through POST /v1/videos.

Output controls#

Use duration=-1 for smart duration or 2-30 seconds. Resolutions are 480p, 720p, and 1080p; aspect_ratio supports adaptive, 16:9, 4:3, 1:1, 3:4, and 9:16.

Polling#

Poll GET /v1/videos/{video_id} until status is completed or failed.