Repository Public
1<br />23Gemini Omni Flash is a high-performance model for fast, conversational video4generation and editing. It excels at turning text and images into video,5lets you refine and edit generated videos through natural language6conversations using the Interactions API, and supports video extension,7resolution upscaling, and advanced interpolation.8[Try in Google AI Studio](https://aistudio.google.com?model=gemini-omni-1.1-flash)910## Documentation1112Visit the [Gemini Omni Flash](https://ai.google.dev/gemini-api/docs/omni)13page for full coverage of features and capabilities.1415## gemini-omni-1.1-flash1617| Property | Description |18|---|---|19| Model code | **Gemini API** `gemini-omni-1.1-flash` |20| Supported data types | **Input** Text, Image, Video (up to 10s for editing and extension) **Output** Video |21| Limits | **Context window** 1,048,576 tokens **Output video** 3s-10s (360p/720p/1080p/4K, 24 FPS) |22| Versions | [Model versions:](https://ai.google.dev/gemini-api/docs/models#model-versions) - Stable: `gemini-omni-1.1-flash` - Preview: `gemini-omni-flash-preview` |23| Latest update | August 2026 |