Google Omni 1.1 Flash: Generates 10 seconds of content per run, supporting a maximum continuous extended generation of up to 40 seconds.

Beating AI News Brief: Google has launched Gemini Omni 1.1 Flash, an updated version of Gemini Omni Flash that debuted in May and opened its API beta at the end of June. The new version still generates videos up to 10 seconds per single output, but adds video continuation support to the Omni API for the first time. After generating a video, users can extend it further, adding up to 10 seconds each time, with a maximum total length of 40 seconds for a continuously extended video. When extending, the model references up to 10 seconds of previous footage to ensure characters, actions, and plot flow smoothly. Omni 1.1 also adds start and end frame control: users can provide a starting image and an ending image, and the model will automatically generate the continuous video in between. For example, if specifying a shot where a character starts in the distance and ends up in front of the camera, the model will fill in the entire movement sequence. A cheaper 360p draft mode is also introduced, with the official noting system throughput is boosted by up to 60% and costs roughly one-third of 720p. API pricing is set at $0.03 per second for 360p, $0.10 for 720p, $0.15 for 1080p, and $0.30 for 4K. Notably, 1080p and 4K outputs are upscaled, not native high-resolution generation.