Gemini Omni 1.2 Flash: 15-Second AI Videos for 30% Less

Google's Gemini Omni 1.2 Flash makes 15-second video clips, edits them turn by turn, and costs $0.07 a second at 720p, 30% less than Omni 1.1.

4 min read

Gemini Omni 1.2 Flash: 15-Second AI Videos for 30% Less

Illustration made on Lumeta with GPT Image 2.5Make one like it

Google released Gemini Omni 1.2 Flash on November 5, 2026. It is the newest version of Google's fast video model, and it makes clips up to 15 seconds long, up from 10 seconds in Omni 1.1. It is also cheaper: Google lists 720p video at $0.07 a second, 30% less than the version before it. The model is generally available in the Gemini API and on Google Cloud, and it is rolling out in Google's own apps.

For creators, the longer clip is the headline. Fifteen seconds is enough for a full product shot, a short scene with dialogue, or a social clip that does not need stitching. The lower price means more takes for the same budget.

What changed in Omni 1.2 Flash

  • Longer clips. You pick any length from 3 to 15 seconds, in one-second steps.
  • Edit by talking to it. You can change a finished clip turn by turn, such as swapping a product or a background, changing the light or the weather, or switching the aspect ratio, without starting over. Google says this works across a full 15-second clip.
  • Draft cheap, finish sharp. Drafts come out at 360p or 720p, and you upscale the best take to 1080p or 4K.
  • References. You can guide a clip with images of a character, product or style, short motion clips of up to three seconds, and audio cues. Google says faces, clothing, packaging text and brand colors hold steady across camera angles.
  • Better voices. Google promises more natural dialogue, cleaner lip sync, and the ability to give each sampled voice to a specific character.
  • Steadier camera moves, with fewer unwanted jump cuts.
Clay figure in a blue cap and Google logo badge sits in a director's chair holding a stopwatch, beside a film camera and gold coins
Fifteen seconds on the clock, and a slightly shorter stack of coins to pay for them.

Illustration made on Lumeta with GPT Image 2.5Make one like it

How much it costs

Google bills Omni 1.2 Flash by output tokens at $12 per million for video, down from $17.50 for Omni 1.1. On Google's pricing page, checked November 16, 2026, that works out to about $0.07 a second at 720p, so a 10-second clip is about $0.70 and a 15-second clip about $1.04. Omni 1.1 was about $0.10 a second at 720p.

Gemini Omni 1.2 Flash: approximate price per second of video
360p$0.02 per second
720p$0.07 per second
1080p (upscaled)$0.10 per second
4K (upscaled)$0.21 per second
Google's Gemini API pricing page, Standard tier, November 16, 2026

Where you can use it

  • Developers: the Gemini API (try it in Google AI Studio) and Vertex AI on Google Cloud, model name gemini-omni-1.2-flash.
  • Gemini app: 15-second videos are rolling out to Google AI Ultra subscribers.
  • Flow, Google's filmmaking app, for directing scenes and making edits over several turns.
  • Google Vids, where Google says 15-second clips come at no extra cost with a Google account or Workspace plan.
  • Google Ads, inside Asset Studio, for video campaigns.

Every clip carries Google's invisible SynthID watermark. Google also says the model still has trouble with fast sports action, quick script changes and complex physics.

Try Gemini Omni on Lumeta

Our Gemini Omni tool runs Google's Omni Flash 1.1 today, with clips from 3 to 10 seconds. You can create a video from a prompt, or attach a video and describe what should change.

Gemini OmniMake or edit a short video with Google's Gemini Omni Flash

When did Gemini Omni 1.2 Flash come out?

Google released it on November 5, 2026, generally available in the Gemini API and on Google Cloud.

How long can a Gemini Omni 1.2 Flash video be?

From 3 to 15 seconds, set in one-second steps. Omni 1.1 stopped at 10 seconds.

How much does a 15-second clip cost?

About $1.04 at 720p in the Gemini API, by Google's own pricing page. 360p is cheaper, and 1080p and 4K cost more because they are upscaled.

Can I edit a clip without making it again?

Yes. You can ask for changes over several turns, such as a new background, different light or another aspect ratio, and the model changes the clip you already have.

Every top AI model, in one place

Nano Banana 2, GPT Image 2.5, Seedance, Veo and more, all on one credit balance. Start free with 35 credits a month. No card needed.

All tools for "From a description"

More from Lumeta

All News