Any-input video generation and scene-preserving video editing with synchronized audio, strong physical motion, and automatic routing for text, images, reference images, and video edits.
Added Jun 30, 2026
Approx. Price
$0.390 per video
Model Type
both
Settings
Generation controls available for this model.
Output Format
Default Duration
8
8 duration options
Aspect Ratio
Default
16:9
Options (2)
Landscape (16:9), Portrait (9:16)
Output aspect ratio
Duration
Default
8
Options (8)
3 seconds, 4 seconds, 5 seconds, 6 seconds +4 more
Video duration in seconds
Benchmarks
Benchmarks
Human preference benchmarks sourced from Artificial Analysis.
Text to Video
#1 / 78
ELO
1322.0
Appearances
5,770
95% CI
-10/10
Image to Video
#1 / 72
ELO
1366.0
Appearances
4,178
95% CI
-12/12
Release Date 2026-05 · Matched as Gemini Omni Flash
Artificial Analysis APIExamples
Loading examples…
Related video models
Compare Gemini Omni Flash with similar models from the same provider or model family.
Gemini Omni Flash 1.1
google/gemini-omni-flash/v1.1Google’s multimodal video model for text-to-video, image animation with optional end frames, multimodal reference generation, and instruction-based video editing. Generates synchronized native audio at resolutions from 360p through 4K.
Veo 3.1 Fast
veo3-1-fast-videoFast Veo 3.1 generation for text-to-video, image-to-video, and reference-to-video with up to 3 total images. Supports optional end frame control for image-to-video, native audio, and 4/6/8 seconds at 720p or 1080p.
Veo 3.1 Lite
veo3-1-lite-videoUnified Veo 3.1 Lite entry for text-to-video, image-to-video, and first/last-frame video generation. Supports 4/6/8 seconds at 720p or 1080p.
Veo 3.1 Extend
veo3-1-extendExtend Veo 3.1 videos by 7 seconds per call with smooth motion, preserved style, and strong scene coherence. Input must be Veo 3.1 generated. Supports up to 20 extensions for max 148 seconds total. 16:9 or 9:16 aspect ratio, 720p or 1080p.
Veo 3.1 Fast Extend
veo3-1-fast-extendFast video extension for Veo 3.1 clips. Adds 7 seconds per call with optimized speed for quick iteration. Input must be Veo 3.1 generated. Supports up to 20 extensions for max 148 seconds total. 16:9 or 9:16, 720p or 1080p.
Veo 3.1
veo3-1-videoText-to-video and image-to-video with optional end frame control. Native audio generation, cinematic realism, and consistent subjects. Supports 4/6/8 seconds at 720p or 1080p.