Gemini Omni 1.2 Flash Adds 15-Second Clips
Google released Gemini Omni 1.2 Flash on Nov. 5, extending AI video clips to 15 seconds from 10 and cutting the 720p price 30% to $0.07 per second, with general availability on the Gemini API and Google Cloud.
Google on Nov. 5 released Gemini Omni 1.2 Flash, an update to its generative video model that stretches single clips to 15 seconds and cuts the 720p price by 30% to $0.07 per second, according to a post on Google's official blog by Anish Nangia, a product manager at Google DeepMind.
Key takeaways
- Clips now run up to 15 seconds, up from 10 seconds in Omni 1.1, with length set in one-second steps from 3 to 15 seconds.
- Google lists 720p output at $0.07 per second, 30% below Omni 1.1. Prices for other resolutions were not given in the post.
- The model is generally available on the Gemini API and Google Cloud, and is rolling into Flow, Google Vids, the Gemini app and Google Ads.
Gemini Omni 1.2 Flash: what changed
The headline change is length. Omni 1.1 capped a single generation at 10 seconds. Version 1.2 reaches 15 seconds, and developers can pick any whole-second duration between 3 and 15.
Google also says editing now works across the full clip. Users can refine a 15-second video through multi-turn conversation instead of regenerating from scratch. Reference inputs have been tightened: the model accepts character, product or style images, short motion clips of up to three seconds, and audio cues.
The post describes "more fluid, natural-sounding dialogue, clearer lip-sync, and distinct multi-speaker conditioning," along with fewer jump cuts during camera moves. Google did not publish benchmark scores for the release.
Gemini Omni pricing per second
"We have dropped the price 30% from Gemini Omni 1.1 making it available at $0.07 per second for 720p video," Nangia wrote. Omni 1.1 listed 720p at $0.10 per second when it shipped in August, so a full 15-second 720p clip now costs about $1.05, roughly what a 10-second clip cost before.
The workflow Google recommends is to draft at 360p or 720p and then upscale winners to 1080p or 4K. The Gemini API changelog notes that 1080p and 4K output from the Omni Flash line is produced by upscaling rather than native generation.
Where developers and users can get it
Google says the model is generally available on the Gemini API and Google Cloud, with Provisioned Throughput for reserved capacity. The AI Studio link in the announcement uses the model string gemini-omni-1.2-flash.
On the consumer side, 15-second clips are coming to Flow and to Google Vids, where Google says they come at no additional cost with a Google account or Workspace subscription. The Gemini app is rolling them out to Google AI Ultra subscribers, and the model is also reaching Google Ads. All outputs carry an imperceptible SynthID watermark, according to the post.
Context: a fast release cadence
The Omni Flash line has moved quickly. The Gemini API changelog shows a public preview on June 30 that produced 3- to 10-second videos at 720p, followed by general availability of gemini-omni-1.1-flash on Aug. 27. Version 1.2 arrives about 10 weeks later.
As of the newest entry checked, dated Oct. 30, the API changelog did not yet list version 1.2, and Google's general pricing page did not include Omni rates. Teams budgeting for 1080p or 4K work should confirm current rates in AI Studio before committing.
What's next
Fifteen seconds covers a typical short ad or social spot in a single generation, which reduces stitching between shots. The open questions are price at higher resolutions and whether native high-resolution output follows the upscaling approach.
FAQ
How long can a Gemini Omni 1.2 Flash clip be?
Up to 15 seconds per generation, selectable from 3 to 15 seconds in one-second steps.
How much does it cost?
Google lists $0.07 per second for 720p video, 30% below Omni 1.1. Other resolution prices were not stated in the announcement.
Is AI-generated video from Omni labeled?
Google says every output carries an imperceptible SynthID watermark.
References
Editor responsible for AI Newsway. Writes about AI, developer tools, cloud and productivity technology.
Comments 0
Comments are currently disabled.