Veo 3.1 Fast — Reference to Video

Generate videos using reference images with Google’s Veo 3.1 Fast model

POST /v1/jobs/submit

Veo 3.1 Fast — Reference to Video

cURL

curl --request POST \
  --url https://api.muvi.video/v1/jobs/submit \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "input": {
    "prompt": "<string>",
    "image_urls": [
      "<string>"
    ],
    "aspect_ratio": "<string>",
    "resolution": "<string>",
    "duration": "<string>",
    "has_sound": "<string>",
    "seed": 123
  }
}
'

200

{
  "jobId": "<string>",
  "status": "<string>",
  "estimatedCompletionTime": "<string>",
  "costMicroCents": 123
}

Generate videos using one or more reference images to guide the visual style and content with Google’s Veo 3.1 Fast model.

Property	Value
Provider	Google
Model	Veo 3.1 Fast
Capability	Reference to Video
Base Cost	200,000 micro-cents/second ($0.20/sec)
Processing Time	~240 seconds

Request Body

model · string · required

Model slug. Use google/veo-3.1-fast/reference-to-video for reference-to-video generation.

input · object · required

Input parameters for reference-to-video generation.

Hide properties

prompt · string · required

Text description guiding the generation (max 4000 characters).

image_urls · string[] · required

Array of reference image URLs (minimum 1, maximum 3).

aspect_ratio · string

Video aspect ratio. Default: 16:9. Options: 16:9, 9:16.

resolution · string

Output resolution. Default: 720p. Options: 720p, 1080p, 4k.

duration · string

Video duration in seconds. Default: 8. Options: 4, 6, 8.

has_sound · string

Enable audio generation. Default: true. Options: true, false.

seed · integer

Seed for reproducible results.

webhookUrl · string

HTTPS URL to receive a webhook notification when the job completes or fails.

Pricing

Base cost: 200,000 micro-cents per second ($0.20/sec)

finalCost = baseCost × duration × resolution × has_sound

Factor	Option	Multiplier
Duration	4	4x
	6	6x
	8	8x
Resolution	720p	1x
	1080p	1x
	4k	1.5x
Sound	false	1x
	true	1.5x

Default cost: 8 seconds, 720p, with sound = 200,000 × 8 × 1 × 1.5 = 2,400,000 micro-cents ($2.40)

Response

jobId · string

Unique identifier for the submitted job.

status · string

Initial job status. Always "pending" on successful submission.

estimatedCompletionTime · string

ISO 8601 timestamp of the estimated completion time.

costMicroCents · number

The cost of the job in micro-cents.

Code Examples

cURL

curl -X POST https://api.muvi.video/v1/jobs/submit \
  -H "Authorization: Bearer $PIXELBYTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/veo-3.1-fast/reference-to-video",
    "input": {
      "prompt": "A cinematic scene combining the visual elements from the reference images",
      "image_urls": [
        "https://example.com/reference1.png",
        "https://example.com/reference2.png"
      ],
      "aspect_ratio": "16:9",
      "resolution": "1080p",
      "duration": "8",
      "has_sound": "true"
    }
  }'