# Gemini Omni 1.2 Flash makes 15-second videos, 30% cheaper

> Google's video model now runs up to 15 seconds, costs $0.07 per second at 720p, and is generally available in the Gemini API and Google Cloud.

URL: https://claudegpt.si/news/gemini-omni-1-2-flash-video-30-percent-cheaper  
Published: 2026-11-05T18:51:44.184Z  
Author: ClaudeGPT Si Newsroom  
Section: AI Models  
Topics: Google, Gemini, Video generation, Gemini API  
Publisher: ClaudeGPT Si

## Key takeaways

- Google released Gemini Omni 1.2 Flash on November 5, 2026, with clips up to 15 seconds, up from 10 in Omni 1.1.
- Google priced it 30% below Omni 1.1, at $0.07 per second of 720p video.
- It is generally available in the Gemini API and Google Cloud, and rolling out in the Gemini app to Google AI Ultra subscribers.

Google released Gemini Omni 1.2 Flash on November 5, its video generation and editing model, with clips up to 15 seconds long and a price 30% lower than Omni 1.1. The model is generally available in the [Gemini API and on Google Cloud](https://blog.google/innovation-and-ai/technology/developers-tools/introducing-gemini-omni-1-2-flash/), and Google lists the price at $0.07 per second of 720p video.

Omni 1.1 topped out at 10 seconds. For people who make product videos or ads in volume, a longer clip at a lower price is the whole pitch, and Google describes the model as built for businesses, developers and creators producing video at scale.

## What changed from Omni 1.1

- **Length.** Clips run from 3 to 15 seconds, set in one-second steps.
- **References.** The model takes character, product or style images, motion clips of up to 3 seconds, and audio cues, and Google says it keeps those details steady from start to finish.
- **Editing.** You can refine a clip in conversation, for example swapping a product or background, changing the lighting or switching the aspect ratio, without regenerating from scratch. It also does first-to-last keyframe interpolation and clip extension.
- **Speech and camera.** Google claims more natural dialogue, clearer lip-sync and multi-speaker support, plus complex camera moves with fewer jump cuts.
- **Workflow.** Draft at 360p or 720p, then upscale to 1080p or 4K.

These are Google's claims, based on its own examples. The post does not cite an independent benchmark. Google says it is still improving fast sports action, rapid script changes and complex physics.

## Price and where to use it

The $0.07 per second figure is for 720p. OpenRouter also lists the model, at $1.50 per million input tokens and $9 per million output tokens, with a 131,072-token context window.

Outside the API, Google says the model is in Flow, in Google Vids (15-second clips at no extra cost with a Google account or Workspace subscription), in Google Ads, and in the Gemini app, where the 15-second videos are rolling out to Google AI Ultra subscribers. Outputs carry a SynthID watermark, which is invisible to viewers.

Google Cloud's [announcement](https://cloud.google.com/blog/products/ai-machine-learning/gemini-omni-1-2-flash-generally-available/) adds Provisioned Throughput for enterprise customers, who can reserve capacity.

Next to watch: independent comparisons against rival video models, which Google's post doesn't include.

## 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
- [Gemini Omni 1.2 Flash is generally available on Google Cloud](https://cloud.google.com/blog/products/ai-machine-learning/gemini-omni-1-2-flash-generally-available/), Google Cloud
- [Google: Gemini Omni 1.2 Flash](https://openrouter.ai/google/gemini-omni-1.2-flash), OpenRouter