Skip to main content

​
Identifier

Use the model identifier veo-3.1-flf in the model field when calling /asset/start.

​
Capabilities

PropertyValue
Reference inputs2
Input typesimage + image
Aspect ratios16:9, 9:16 (default 9:16)
Resolutions720p, 1080p (default 720p)
Durations (seconds)4, 6, 8 (default 8)
Audioyes
Tagsfirst-last-frames

​
Inputs

This model takes named media inputs. Pass each one as a top-level field in the request body (not inside references). Each field accepts exactly one of url, asset_id, or avatar_id.
FieldTypeRequiredDescription
first_frameimageyesImage used as the first frame of the generated video.
last_frameimageyesImage used as the last frame of the generated video.
  • url — a direct, publicly accessible file URL
  • asset_id — the ID of an existing asset in your Hoox space (e.g. a previous generation)
  • avatar_id — the ID of an avatar defined in your Hoox space

​
Custom settings

These keys go inside the model_settings object of the request body.
KeyTypeDefaultAffects cost
generateAudiobooleantrueyes

​
Pricing

Default parameters (8s at 720p): ~32 credits / generation. For exact pricing with your own parameters, call /asset/pricing with the model and any parameters that affect cost.

​
Example request

{
  "type": "video",
  "model": "veo-3.1-flf",
  "prompt": "Describe what you want to generate",
  "first_frame": {
    "url": "https://example.com/reference.jpg"
  },
  "last_frame": {
    "url": "https://example.com/reference.jpg"
  },
  "aspect_ratio": "9:16",
  "resolution": "720p",
  "duration": 8
}
See /asset/start for the full request/response reference, error codes, and code samples in cURL / Python / JavaScript.