Gemini Omni 1.1 Flash: 40s Video, 4K Upscale
Summary: Gemini Omni 1.1 Flash in 30 Seconds Gemini Omni 1.1 Flash is Google’s video generation model, released on 27 August 2026. It replaces Veo 3.1 on the video side. A single generation is still 10 seconds. The headline “40 seconds” is a cumulative length you reach by extending the same video in 10-second steps. When extending, the model now reads up to 10 seconds of prior footage. Previous models only referenced the final second, which is where the consistency gain comes from. You can pin the first and last frame and let the model generate the motion between them. Built for orbit shots, transitions and looping clips. The 360p draft tier runs up to 60% faster at one third of the cost of 720p. Google’s recommended loop: draft at 360p, render the pick at 720p, upscale to 1080p or 4K at the end. 4K is an upscale, not native generation. The model generates 720p; anything above that is an enlargement. Per second: 360p $0.03 · 720p $0.10 · 1080p $0.15 · 4K $0.30. In tokens, $1.50 per million in and $17.50 per million for video out. The API has real gaps: no system instructions, no function calling, no structured output, no context caching. The problem with Google’s video models for the past year was length. An 8-10 second clip is impressive but it isn’t a scene. Gemini Omni 1.1 Flash doesn’t fix that by making the clip longer, it fixes it by making clips stackable. ...