Gemini Omni Flash

Google multimodal model that builds video from text, images, and video, and can edit an existing clip conversationally. Use it when you need to transform footage or mix inputs rather than generate a shot from scratch. Synchronized audio, up to 4K.

Cost

from 20 tokens

VideoProvider: Google
Run generation
IDEMPOTENCY_KEY="${IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.givon.ai/api/v1/generations \
  -H "Authorization: Bearer $GIVON_API_KEY" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"video","model":"gemini-omni-video","input":{"prompt":"cinematic drone shot over a city at night","aspectRatio":"9:16","resolution":"720p","duration":4,"referenceAssetUris":["asset://asset_..."]}}'

Input fields

* required
prompt*prompt

Generation prompt describing the scene, action and direction.

Type
string
Default
Allowed
up to 5000 chars
aspectRatioaspectRatio
Type
string
Default
9:16
Allowed
16:9, 9:16
resolutionresolution
Type
string
Default
720p
Allowed
720p, 1080p, 4k
durationduration
Type
number
Default
4
Allowed
4, 6, 8, 10
Start imagestartImage

Asset input for the startImage slot.

Type
string
Default
Allowed
image · asset, https, data
Source videosourceVideo

Asset input for the sourceVideo slot.

Type
string
Default
Allowed
video · asset, https, data
Reference imagesreferenceAssetUris

Optional reference assets as asset:// URIs, HTTPS URLs, or data URIs.

Type
array
Default
Allowed
image · up to 7 · asset, https, data

Cost

from 20 tokens
720p- 4sdefault20 tokens
720p- 6s23 tokens
720p- 8s28 tokens
720p- 10s35 tokens
1080p- 4s28 tokens
1080p- 6s35 tokens
1080p- 8s44 tokens
1080p- 10s52 tokens
4k- 4s62 tokens
4k- 6s72 tokens
4k- 8s90 tokens
4k- 10s100 tokens
Video- 720p72 tokens
Video- 1080p72 tokens
Video- 4k90 tokens

The variant is selected automatically from request fields, so you do not need to send it.

Capabilities

Modesvideo_edittext_image_to_videoimage_to_videotext_to_video
Asset slotsstartImage:imagesourceVideo:videoreferenceAssetUris:image[]<=7

Run Gemini Omni Flash

Get an API key and the same request shape will work across every model in the catalog.

Where to use this model

Gemini Omni Flash API - video generation · Givon AI