Google's Gemini Omni 1.1 Flash adds 40-second video extension, frame pinning, and 4K output
- Gemini Omni 1.1 Flash extends clips in 3 to 10-second calls to a 40-second total, using up to 10 seconds of earlier video context and editing input end frames to smooth the join.
- The API supports first- and last-frame pinning to generate a clip between fixed endpoints, plus up to three 3-second video references for likeness consistency; reference audio is ignored.
- Google recommends a draft-then-upscale workflow: 360p previews are reported to generate up to 60% faster and cost one-third of 720p, while 1080p and 4K outputs are upscaled.
- Pricing is listed at $1.50 per 1 million input tokens and $17.50 per 1 million video tokens, with 720p video billed at 5,792 tokens per second, or about $0.10 per second.
- The model is available in the Gemini API, Google AI Studio, Gemini Enterprise Agent Platform, and Google Flow, but lacks voice editing, audio references, negative-prompt parameters, and mid-clip insertion.