Gemini Omni 1.2 Flash Is Live: 15-Second AI Video for About $1.04 a Clip

Google has made Gemini Omni 1.2 Flash generally available, and the headline change is time: the model now generates and edits native video up to 15 seconds long, up from 10 seconds with Omni 1.1. It costs 30% less than its predecessor — $0.07 per second for 720p video, which Google prices at about $1.04 for a full 15-second clip. The catch is access: it is available only on the paid tier of the Gemini API, with no free tier, and the 15-second option in Flow needs a paid Google AI plan.

Omni 1.2 Flash is Google's video generation and editing model — the engine behind video creation in the Gemini API, Flow, Google Vids, and the Gemini app. The 5 November 2026 launch is a general availability release, not a preview, which means developers can build on it now.

Illustration created for INORYVA

What is new: 15 seconds, in one-second steps

The core upgrade is duration. Omni 1.2 Flash generates and edits video up to 15 seconds, where Omni 1.1 stopped at 10, and you can specify the duration in one-second increments from 3 to 15 seconds. Five extra seconds may sound small, but in video generation it is a 50% increase in length — enough to turn a fragment into a complete shot, with a beginning, a middle, and an end.

The second upgrade is multi-turn conversational editing. Instead of generating a clip, rejecting it, and starting over, you can refine the same clip turn by turn — swapping a product, changing a background, adjusting lighting or weather, or changing the aspect ratio — while keeping the rest of the shot intact.

The third upgrade is stronger reference following. You can guide generation with character, product, or style images, short motion clips of up to 3 seconds, and audio cues — and Google says faces, garments, packaging typography, and brand colours stay consistent.

Feature	Omni 1.1 Flash	Omni 1.2 Flash
Maximum clip length	10 seconds	15 seconds
Multi-turn editing	Limited	Full 15-second clips, turn by turn
Video output price	$17.50 per 1M tokens	$12.00 per 1M tokens (30% cheaper)
15-second clip (video output)	Not possible	~$1.04

What it costs — and what the $1.04 figure leaves out

The pricing is where precision matters. Google's blog says Omni 1.2 Flash is 30% cheaper than Omni 1.1, at $0.07 per second for 720p video. The API pricing page gives the exact basis: video output costs $12.00 per million tokens, down from $17.50 for Omni 1.1, and 720p video uses 5,792 tokens per second — about $0.0695 per second. Google's own stated totals are about $0.70 for a 10-second clip and about $1.04 for a 15-second clip.

Two more costs sit outside that headline number. Input tokens cost $1.50 per million, and text output costs $9.00 per million — both extra, on top of the video output price. Upscaling to 1080p or 4K is upsampling, not native rendering: the pricing page lists $0.104 per second for 1080p with upsampling and $0.209 per second for 4K with upsampling, so a 15-second 4K clip costs more than three times the 720p price.

Most importantly, Omni 1.2 Flash is available only on the paid tier of the Gemini API. The pricing page states it is "now generally available to developers on the paid tier of the Gemini API", and the free-tier column reads "Not available" for both input and output. There is no free-tier path to this model through the API. Readers comparing it with the Gemini free tier Flash-Lite explained story should note the difference: Flash-Lite is the free-tier option, Omni 1.2 Flash is not.

Illustration created for INORYVA

Where you can use it: API, Flow, Vids, and the Gemini app

Google is rolling Omni 1.2 Flash out across four surfaces, and the 15-second option is not equal in all of them. In the Gemini API, the model is generally available on the paid tier. In Flow, Google's AI filmmaking tool, you can direct scenes and make multi-turn edits. In Google Vids, you can generate 15-second clips at no additional cost with a Google account or Google Workspace subscription. In the Gemini app, 15-second videos are rolling out to Google AI Ultra subscribers.

Flow has the most detailed rules: generating or editing 15-second clips, extending a clip by 3 to 10 seconds, and upscaling to 720p or 1080p all require a Google AI Plus, Pro, or Ultra subscription, and upscaling to 4K needs Ultra specifically. The free tier of Flow gets the model, but not its headline features.

Flow's credit costs follow a per-second structure that Google publishes on its help page. For clips up to 10 seconds, the rate is 1 credit per second at 360p and 3 credits per second at 720p. For the extra seconds from 11 to 15, the rate rises to 2 credits per extra second at 360p and 6 credits per extra second at 720p. Working from those published rates, a 15-second 720p clip costs 30 credits for the first 10 seconds plus 30 credits for the extra five — 60 credits in total. That total is calculated from Google's per-second rates, not a figure Google prints.

What is being retired

The launch comes with two retirement dates that existing users need to know. From 3 December 2026, all API requests to gemini-omni-1.1-flash will automatically route to gemini-omni-1.2-flash and be billed at 1.2 rates — the old model simply stops being served. On 5 December 2026, Veo 3.1 Fast, Veo 3.1 Quality, and Omni Flash 1.1 will be retired in Flow. Veo Extend was already retired on 5 November 2026, the same day Omni 1.2 launched: to extend a video now, you must be a Google AI Plus, Pro, or Ultra subscriber and use Omni Flash 1.2.

That is a fast transition — less than a month between the new model's launch and the old one's retirement — and for API users the migration is automatic on 3 December whether they are ready or not.

Omni is now the single video model across the API and Flow, replacing Veo 3.1 in Flow entirely. Readers following the video-model race will remember Kling 4.0's 30-second AI videos — twice Omni's new maximum — so Google is still behind on raw length, and its bet is editing, reference consistency, and price.

Illustration created for INORYVA

Who should care

For developers, Omni 1.2 Flash is a genuine improvement at a lower price — 15 seconds, multi-turn editing, and a 30% cut on the paid API tier, with existing integrations auto-routed to it on 3 December. For creators using Flow, the value depends on the subscription: free users get the model but not the 15-second clips, Extend, or upscaling, while Plus, Pro, and Ultra subscribers get the full feature set. For Vids users, the 15-second option at no additional cost with a Google account or Workspace subscription is the simplest deal in the launch.

The honest summary: Google now offers the cheapest short-form video generation in its own lineup, with the best editing workflow. The Gemini 4 Carbon launch showed Google pushing its flagship models hard; Omni 1.2 Flash applies the same push to video — cheaper, longer, and easier to edit, but only if you are paying.

Key Takeaways

• Gemini Omni 1.2 Flash is generally available from 5 November 2026, generating and editing native video up to 15 seconds — up from 10 seconds with Omni 1.1 — in 1-second steps from 3 to 15 seconds.
• Multi-turn conversational editing lets you refine the same clip turn by turn, and stronger reference following keeps faces, garments, packaging typography, and brand colours consistent.
• It is 30% cheaper than Omni 1.1: $12.00 per 1M tokens for video output, about $0.07 per second at 720p — Google's own totals are ~$0.70 for a 10-second clip and ~$1.04 for a 15-second clip. Input and text-output tokens cost extra.
• It is available only on the paid tier of the Gemini API — the free tier reads "Not available". In Flow, 15-second clips, Extend, and upscaling need a paid Google AI plan; a 15-second 720p clip costs 60 credits by Google's published per-second rates, against a 50-credit daily allowance.
• Omni 1.1 auto-routes to 1.2 from 3 December 2026, and Veo 3.1 Fast, Veo 3.1 Quality, and Omni Flash 1.1 retire in Flow on 5 December 2026. Veo Extend was already retired on 5 November.
• Upscaling to 1080p or 4K is upsampling, not native rendering, and costs $0.104 and $0.209 per second respectively.

Conclusion

Gemini Omni 1.2 Flash is a solid, well-priced upgrade: 50% more video per clip, multi-turn editing, stronger reference consistency, and a 30% price cut to about $1.04 per 15-second 720p clip. The limits are just as real — no free tier on the API, paid plans required for the headline features in Flow, and a forced migration as Veo 3.1 and Omni 1.1 retire in December. On price and editing, though, it is now the most practical video model in Google's lineup — for anyone willing to pay for it.

Sources

• Google — "Introducing Gemini Omni 1.2 Flash" — https://blog.google/innovation-and-ai/technology/developers-tools/introducing-gemini-omni-1-2-flash/
• Google AI for Developers — Gemini API pricing — https://ai.google.dev/gemini-api/docs/pricing
• Google Flow Help — "Flow credits and limits" — https://support.google.com/flow/answer/16526234

Facts checked against Google's own blog, API pricing page, and Flow help page on 6 November 2026. The 60-credit total for a 15-second 720p Flow clip is calculated from Google's published per-second rates, not a figure Google prints.