Google DeepMind has released version 1.1 of its Gemini Omni Flash model with 1080p and 4K output options, replacing the native 720p resolution introduced at Google I/O in May 2026. The model generates 3 to 10 second video clips with synchronized audio from multimodal inputs including text, images, audio, and video. The API pricing for the 720p version is currently 0.10 dollars per second of generated video, equaling one dollar for a 10-second clip, with new tier pricing not yet announced. Developer API access entered public preview on June 30, 2026, and all generated content includes SynthID watermarking. Omni Flash is available to Google AI Plus, Pro, and Ultra subscribers, as well as free through YouTube Shorts and YouTube Create.
Source: Read the original article
