# Gemini Omni 1.2 Flash: 15s video, 30% cheaper, now GA

> Gemini Omni 1.2 Flash adds 15-second video, multi-turn editing and a 30% price cut to $0.07 per second at 720p. Here is what founders should know.

- URL: https://tools.launchllama.co/blog/gemini-omni-1-2-flash-15-second-video-30-percent-cheaper
- Published: 2026-11-06
- Publisher: Launch Llama (https://tools.launchllama.co)

TL;DR
- Gemini Omni 1.2 Flash generates native video up to 15 seconds (Omni 1.1 topped out at 10) and is generally available on the Gemini API and Google Cloud.
- Price is $0.07 per second for 720p video, a 30% drop from Gemini Omni 1.1.
- You can edit a clip over several turns (swap a product, background or lighting) instead of regenerating, and references hold up better across shots.

## What happened

On Nov 5, 2026, Google DeepMind released Gemini Omni 1.2 Flash. It is generally available across the Gemini API and Gemini for business, backed by Google Cloud. Provisioned Throughput is available, and outputs carry an imperceptible SynthID watermark.

The main changes: native clips up to 15 seconds (up from 10 in Omni 1.1), with duration set in one-second steps from 3 to 15 seconds. Multi-turn conversational editing works across full 15-second clips. Google also says reference adherence is better. You can combine character, product or style images, motion clips of up to three seconds, and audio cues, and faces, garments, packaging typography and brand colors should stay consistent across camera angles.

Price is $0.07 per second for 720p video, 30% lower than Omni 1.1. Google describes a cheaper workflow: draft at 360p or 720p, fix details with a follow-up edit, then upscale the best result to 1080p or 4K. The source does not give prices for 1080p or 4K, so those are not confirmed. Google also says fast sports action, rapid script changes and complex physics are still being improved.

## What this means for founders

- **Cost math is easy now.** At $0.07 per second for 720p, a full 15-second clip is $1.05 per generation at that resolution. Multiply by the number of drafts you expect, since you will rarely keep the first one.
- **Fewer re-generations.** Multi-turn editing lets you swap a product, background, lighting or aspect ratio on the same clip. For ad variants across audiences and placements, that is the part most likely to save you money.
- **Product and brand use cases get more realistic.** Google positions it for virtual try-on clips, catalog spins and branded video ads built from existing product photos or character sheets. Test with your own assets before you commit.
- **Production readiness.** It is generally available with Provisioned Throughput, so you are not building on a preview. If you were waiting on that, this removes one reason to wait.
- **Known gaps.** Google itself lists fast sports action, rapid script changes and complex physics as areas still in development. Avoid those in your first tests. Final 1080p and 4K upscale costs are not stated in the source.

## What the Launch Llama directory shows

Live numbers from Launch Llama for listings that describe themselves as "ai video generator", "video editing api", "generative video" tools, as of 2026-11-06.

SignalLaunch Llama dataListings in this space16New in the last 30 days2With a free or freemium plan79%Most upvoted by foundersHappy Horse 1.1 AI Video Generator (36 upvotes)

Launch Llama lists 16 tools in this space, 2 of them added in the last 30 days, and 79% have a free or freemium plan, so expect competition on both price and trial access.

## How to try it today

- Open Google AI Studio and prototype with Gemini Omni 1.2 Flash, then read the developer documentation and pricing page linked from Google's announcement.
- Start with 360p or 720p drafts to keep costs down. Set the duration between 3 and 15 seconds.
- Upload a product photo or character image as a reference, then refine with follow-up prompts instead of regenerating the whole clip.
- Upscale only the best result to 1080p or 4K.
- If you are not coding, try Flow, or Google Vids (15-second clips at no additional cost with a Google account or Google Workspace subscription). The Gemini app is rolling out to Google AI Ultra subscribers. For business use, try the Google Cloud console.

Example first prompt, then edit turn by turn:

Using the attached product photo as reference, make a 15-second clip of the product rotating 360 degrees on a clean studio background. Keep the packaging text and brand colors exact.

Follow-up turn: Keep everything the same, but change the background to an outdoor market and make the lighting warmer.

## Related tools on Launch Llama

Tools from the Launch Llama directory that fit with this news:

ToolWhat it doesWhy it matters hereGemini Omni FlashFor developers: Gemini Omni Flash generates high-quality video from text, images and video inputs via API so you build video features at competitive per-second pricing.Our listing for the earlier Gemini Omni Flash API shows $0.10 per second, so compare it against the new $0.07 per second at 720p for 1.2 Flash.Gemini Omni 1.1 FlashFor developers: Gemini Omni 1.1 Flash generates and edits videos with creative controls so you build multimodal AI applications faster.This is the Omni 1.1 Flash listing, the version that 1.2 Flash improves on with longer clips and a 30% lower price.Gemini omniFor video creators: Gemini Omni generates and edits multimodal videos from text, images, or video—with natural prompt-based control and audio reference workflows.A listing for Gemini Omni covering prompt-based video generation and editing with audio reference workflows, which lines up with the features in this release.

[Browse all tools](https://tools.launchllama.co/tools) or [list your own tool](https://tools.launchllama.co/submit).

## Llama's take

I would try this now if you make product videos, social ads or explainers and you already pay for video generation. The price cut, the 15-second ceiling and editing without starting over all hit real costs. A 30% drop at 720p is large enough to justify a one-afternoon test with your own product shots.

I would wait if your content depends on fast sports action, complex physics or rapid script changes, since Google says those are still being worked on. Also wait on any 1080p or 4K budget until you see the actual pricing for those outputs.

The one thing to watch is how well references really hold up on your assets. The demos are Google's own, so run your own packaging, faces and text before you build a workflow around it.

## FAQ

### How much does Gemini Omni 1.2 Flash cost?

Google lists $0.07 per second for 720p video, which is 30% lower than Gemini Omni 1.1. Prices for 1080p and 4K output are not stated in the source, so check the Gemini API pricing page.

### How long can Gemini Omni 1.2 Flash videos be?

Clips can be up to 15 seconds, up from 10 seconds in Omni 1.1. You can set the duration in one-second steps from 3 to 15 seconds, and multi-turn editing works across full 15-second clips.

### Where can I use Gemini Omni 1.2 Flash?

It is generally available on the Gemini API and Google Cloud, and in Google AI Studio for prototyping. You can also use it in Flow, Google Vids, Google Ads and Gemini for business, and it is rolling out in the Gemini app to Google AI Ultra subscribers.

## Sources

- [Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips](https://blog.google/innovation-and-ai/technology/developers-tools/introducing-gemini-omni-1-2-flash) (Google AI)

---

More for agents: https://tools.launchllama.co/llms.txt · https://tools.launchllama.co/catalog.md · https://tools.launchllama.co/mcp
