Skip to main content
Log inSign up

Filtered — This model refuses requests beyond its own limits outright. Measured, not assumed — models we have not measured carry no label at all.Browse every model at this filtering level
google/gemini-omni-1.2-flash/reference-to-video

Use up to six images and three short video references to guide people, products, places, visual style or motion in a new scene.

From $0.028/s
Run model

Workbench

These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.

  • Output6s
    dining-car-note

    In our tests, two uploaded portraits guided a 6-second 720p railway scene: a note crossed the table, one traveler read it and smiled, and train and cutlery sounds accompanied the exchange.

    • 720p
    • 16:9
    • 6s

This example starts at $0.028 per output second. The Playground updates the estimate when you change the settings.