UniRouteUniRoute

gemini-omni-video

Commercial use

Gemini Omni is Google’s released multimodal creation model built to create from different kinds of input, starting with video. Gemini Omni Flash is the first model in the Omni family, supporting practical video generation and editing workflows such as natural language edits, reference-based creation, scene transformation, and coherent visual storytelling.

Model Type:
Pricing: from $0.079/s · 720p/1080p
View all pricing

gemini-omni-character USD / second

Option / channelOfficialCloud vendor

gemini-omni-video USD / second

Option / channelOfficialCloud vendor
720p/1080p$0.1125$0.0788
4K$0.2625$0.1837

gemini-omni-audio USD / request

Option / channelOfficialCloud vendor

Input

Describe the image you want to generate.362/20000
image_urls
File 1
image_urls 1

File uploads require configured image storage. A public HTTPS image URL can be used directly.

Reference images. The base limit is 7; a video uses 2 image slots and each character_id uses 1 image slot.
Note: when video input is provided, the output duration is determined by the model automatically. This duration parameter will not take effect.
Video ratio
Output video resolution. Valid values: 720P(default), 1080P, 4k.
Random seed. Range: [0, 2147483647]. If not specified, the system generates a seed automatically. Fixing the seed can improve reproducibility, but results may still vary due to the model’s stochasticity.

Output

output typevideoExample output
Download

Examples

Explore different use cases and parameter configurations

README

Complete guide to using gemini-omni-video