Model reference
Veo 3.1
Cinematic Google video model up to 4K with built-in audio, in three tiers: Lite for the lowest price, Fast for balance, Quality for the sharpest result.
| Property | Value |
|---|---|
modelSlug | veo-3-1 |
| Kind | Video |
| Maker | |
Copies per request (variations) | 1 to 5 |
| How the cost is counted | per copy, at a rate that depends on tier and resolution |
| Over MCP | yes, with the generate tool |
Credit amounts are left out because they change. The lowest price is creditCost on GET /v1/models, and POST /v1/jobs answers with the exact creditCost of a request.
input fields
Send the fields below inside the input object. A field you leave out takes its Default. Unknown field names are dropped without an error, so check the spelling if a setting seems to have no effect.
| Field | Type | Required | Default | Rules |
|---|---|---|---|---|
prompt | string | yes | – | – |
tier | string (one of) | – | fast | Tier. lite (Lite), fast (Fast), quality (Quality) |
mode | string (one of) | – | text | text, frames, reference |
frames | string[] (image upload ids) | – | – | Start and end frames. Up to 2 files |
reference_images | string[] (image upload ids) | – | – | Reference images. Up to 3 files |
aspect_ratio | string (one of) | – | 16:9 | 16:9, 9:16, auto |
resolution | string (one of) | – | 720p | 720p, 1080p, 4k |
duration | string (one of) | – | 8 | 4, 6, 8 |
Rules by setting
This model runs a different version depending on what you send. The rules below are checked before any credits move; a request that breaks one is refused with 400 and a message naming the field.
mode = text
- Takes no files in
framesandreference_images; a request that fills one is refused. aspect_ratiotakes only16:9,9:16.
mode = frames
- Takes no files in
reference_images; a request that fills one is refused. frames: required; up to 2 files.
mode = reference
- Takes no files in
frames; a request that fills one is refused. reference_images: required; up to 3 files.tiertakes onlylite(Lite),fast(Fast).durationtakes only8.aspect_ratiotakes only16:9,9:16.
Example request
{
"modelSlug": "veo-3-1",
"input": {
"prompt": "The camera circles slowly around a steaming cup of coffee on a wooden table"
}
}