Skip to main content
POST
  • Asynchronous processing mode, returns a task ID for subsequent status queries
  • Direct connection to Google Vertex AI, supporting all native Veo parameters
  • Supports text-to-video, image-to-video, and keyframe interpolation generation modes
  • Generated video links are valid for 24 hours, please save them promptly
Important Change: For better performance and cost control, we no longer support passing base64 image data directly in image_urls. Please use the Upload Image endpoint to upload images first, then use the returned URL in this API.

Authorizations

string
required
All endpoints require Bearer Token authenticationGet API Key: Visit the API Key Management page to obtain your API KeyAdd to request headers:

Body

string
default:"Veo3.1-quality-official"
required
Video generation model nameAvailable models:
  • Veo3.1-quality-official - High-quality generation model, ideal for final production
  • Veo3.1-fast-official - Fast generation model, ideal for quick previews and iteration
Example: "Veo3.1-quality-official"
string
required
Text description for video generation
integer
Video duration in secondsSupported values:
  • 4 - 4 seconds
  • 6 - 6 seconds
  • 8 - 8 seconds (default)
string
Video aspect ratioSupported formats:
  • 16:9 (landscape, default)
  • 9:16 (portrait)
string
Video resolutionSupported values:
  • 720p (default)
  • 1080p
  • 4k (preview)
string[]
First frame reference image for image-to-video generation. The video will begin from this image. Only the first URL in the array is used.⚠️ Only URL format is supported (base64 is no longer supported)
  • Publicly accessible image URLs (http:// or https://)
  • Use the Upload Image endpoint to upload local images and get URLs
Limits:
  • Maximum file size: 10MB
  • Supported formats: .jpeg, .jpg, .png, .webp
image_urls and metadata.referenceImages cannot be used together. If both are provided, image_urls (first frame) takes priority and referenceImages will be ignored.
object
Veo3 Official specific extension parameters

Response

string
Unique task identifier for querying task status
string
Object type, always generation.task
string
Model name used
string
Task status
  • queued - Queued for processing
  • in_progress - Processing
  • completed - Successfully completed
  • failed - Failed
integer
Task progress percentage (0-100)
integer
Task creation timestamp (Unix timestamp)
object
Task metadata