Gemini Omni 1.2 Flash: 15-Second Clips, $0.07/sec and What Changed From 1.1
Gemini Omni 1.2 Flash is Google's new video generation model, released on November 5, 2026. It makes clips of 3 to 15 seconds, up from 10 seconds in Omni 1.1, and lets you edit a clip in a multi-turn conversation instead of generating it again. It costs $0.07 per second of 720p video, 30% less than Omni 1.1. It is generally available in the Gemini API and Google Cloud, and is rolling out to Google Vids, Flow and the Gemini app. aiwith.chat does not offer Gemini Omni 1.2 Flash yet; its AI Video bot runs Seedance 1.5 Pro and CogVideoX.
Last checked: November 6, 2026. This guide is based on Google's launch post. We have not run our own quality tests on the model.
What's new in Gemini Omni 1.2 Flash
Google lists five changes compared with Omni 1.1 Flash:
- Longer clips. You can generate and edit video up to 15 seconds long in one generation, and set the length in one-second steps from 3 to 15 seconds. Omni 1.1 stopped at 10 seconds.
- Multi-turn editing. You can change a finished clip turn by turn: swap a product or background, change the lighting or weather, or switch the aspect ratio. This works on full 15-second clips.
- Better reference adherence. You can mix character, product and style images, short motion clips of up to 3 seconds, and audio cues. Google says faces, clothes, packaging text and brand colors stay consistent across camera angles.
- More natural speech. Dialogue sounds more fluid, lip-sync is clearer, and each voice can be assigned to a different character in multi-speaker scenes.
- Steadier camera moves. Long FPV flythroughs, zoom-outs and orbits come out with fewer unwanted jump cuts.
Google also says the model still has trouble with fast sports action, rapid script changes and complex physics.
How much does it cost?
Google prices Gemini Omni 1.2 Flash at $0.07 per second for 720p video in the Gemini API. That is 30% cheaper than Omni 1.1 Flash.
Some example costs at that rate:
- A 5-second 720p clip: $0.35
- A 10-second 720p clip: $0.70
- A full 15-second 720p clip: $1.05
Google suggests keeping costs down this way: draft at 360p or 720p, fix details with follow-up edits instead of full regenerations, then upscale the best take to 1080p or 4K. Upscaling and the 360p tier have their own prices on Google's pricing page, so check it before you plan a large batch.
Where you can use it
- Developers: the Gemini API, with prototyping in Google AI Studio.
- Businesses: the Google Cloud console. For the first time, Omni is generally available with Google Cloud's enterprise terms, and Provisioned Throughput is offered.
- Google app users: 15-second clips in Google Vids at no extra cost with a Google account or Workspace plan, scene directing in Flow, and the Gemini app, which is rolling out to Google AI Ultra subscribers first.
- Advertisers: video campaigns in Google Ads.
All outputs carry an invisible SynthID watermark.
Try AI video on aiwith.chat
aiwith.chat does not host Gemini Omni 1.2 Flash at the time of writing. If you want to make a clip today without a Google AI Ultra plan or an API key, aiwith's AI Video bot generates video from text or an image, and you can upload a first and last frame. It runs Seedance 1.5 Pro, which supports sound, and CogVideoX. A clip takes about 2 to 5 minutes, and you can switch pages while it renders.
Try AI Video free on aiwith.chat
Is it worth switching?
- You already pay for Omni 1.1 through the API: switch. You get longer clips and multi-turn edits for 30% less per second.
- You make product, try-on or brand ads: test it first. Reference adherence and multi-turn editing are the changes most likely to matter for you, because they let you make ad variants without rewriting the brief.
- You make sports, fast-action or physics-heavy scenes: wait. Google says these are still weak spots.
- You just want an occasional short clip: you don't need the API. Google Vids gives 15-second clips at no extra cost, and aiwith's AI Video bot works with free signup credits.
Source: Google blog: Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips (November 5, 2026)