VideTShrts

AI video models

The models behind the apps. Most video apps resell a handful of models, so the model decides the quality and the app decides the price and workflow. Open each model to see which apps offer it.

Closed models (use through apps or APIs)

ModelMakerReleasedDoesAudioApps we track
Gemini Omni FlashGoogleMay 2026Text to video, Image to video, Video editingYes2
Veo 3.1GoogleNot statedText to video, Image to videoYes4
Wan 3.0AlibabaAugust 24, 2026Text to video, Image to video, Document to videoYes1
Seedance 2.5ByteDanceJuly 31, 2026Text to video, Image to video, Region editingNot stated2
Kling 3.0KuaishouFebruary 4, 2026Text to video, Image to video, Multi-shotYes4
Runway Gen-4.5RunwayDecember 1, 2025Text to video, Image to videoNot stated2

Open-weight models (run on your own GPU)

Free to download, but each has its own license. Read it before commercial use.

ModelMakerReleasedDoesAudioApps we track
MiniMax H3 (Hailuo 3)MiniMaxJuly 31, 2026Text to video, Image to videoYes2
Wan 2.2Alibaba2025Text to video, Image to videoNot stated-
LTX-2.5LightricksAugust 2026Text to video, Image to videoYes-
HunyuanVideo 1.5TencentNot statedText to video, Image to videoNot stated-

Which model is best?

Public leaderboards built on blind human votes (such as the Artificial Analysis video arena) reshuffle every few weeks, and snapshots disagree. In autumn 2026 Gemini Omni Flash, Wan 3.0, MiniMax H3 and Seedance 2.5 traded the top spots. Use the leaderboard for the current order, then pick by clip length, audio, price and license.

Last checked 2026-11-18. Each model page lists its sources.