Gemini Omni Models by Google DeepMind
Last refreshed 2026-08-28. Next refresh: weekly.
Details
Capabilities
About
Gemini Omni is Google's line of video generation and editing models in the Gemini API. Gemini Omni Flash turns text and images into video and lets you refine and edit a generated video through natural-language conversation using the Interactions API. It also supports video extension, resolution upscaling, and interpolation. It takes text, images, and video (up to 10 seconds for editing and extension) as input and outputs 3- to 10-second clips at 360p, 720p, 1080p, or 4K at 24 FPS. The stable model is gemini-omni-1.1-flash, with gemini-omni-flash-preview as the preview version, and it can be tried in Google AI Studio.
Decision facts
- Best fit
- video generationvision and multimodal work
- Capability starting point
- Gemini Omni 1.1 Flash with 1M context and multimodal inputs
- Lowest tracked input
- Gemini Omni 1.1 Flash · $1.50/1M · Google AI Studio
- Closest related family
- DiffusionGemma
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
Use when the workload needs video generation, 1M context, and multimodal inputs.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Gemini Omni 1.1 Flash | Use when the workload needs video generation, 1M context, and multimodal inputs. | 2026-08 | video generation1M contextmultimodal inputs | Current |
Release Timeline
1 release groupSpecifications(1 models)
| Model | Released | Context | Vision | Multimodal |
|---|---|---|---|---|
| Gemini Omni 1.1 Flash | 2026-08 | 1M | Yes | Yes |
Available From(1 provider)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| Gemini Omni 1.1 Flash | Google AI Studio | $1.5 | $17.5 | Serverless |
