Gemini Omni Flash (Preview) is a multimodal model designed for video, image, and text tasks. It is optimized for video generation, offering video output alongside text responses in a single model.
Try in Agent Studio View in Model Garden Deploy example app
Model ID
gemini-omni-flash-preview
Modalities
Token limits
Maximum input tokens
131,072
Maximum output tokens
57,920
Capabilities
- Supported
- Not supported
- Chat completions
- Image generation
- Interleaved images and text
- Edit images
- Multi-turn image editing
- Grounding with Google Search
- Code execution
- Supervised fine-tuning
- Continuous tuning
- Preference tuning
- Tuning checkpoints
- System instructions
- Function calling
- Gemini Live API
- Implicit context caching
- Explicit context caching
- Supported
- Not supported
Technical specifications
Video
- Maximum video length (with audio): 10 seconds
- Maximum video length (without audio): 10 seconds
- Maximum number of videos per prompt: 3
- Supported MIME types:
video/x-flv,video/quicktime,video/mpeg,video/mpegs,video/mpg,video/mp4,video/webm,video/wmv,video/3gpp
Parameter defaults
- Temperature: 0.0-2.0 (default 1.0)
- topP: 0.0-1.0 (default 0.95)
- topK: -
- candidateCount: 1
Supported regions
Model availability
- Global
- global
Standard pay-as-you-go
- Global
- global
Knowledge cutoff date
-
Versions
-
gemini-omni-flash-preview - Launch stage: Preview
- Release date: June 30, 2026
- Discontinuation date: June 30, 2027
Pricing
