# Google releases Gemini Omni 1.2 Flash, with 15-second videos at a 30% lower price

> A second of 720p video now costs $0.07, billed by tokens. Gemini Omni is generally available for the first time, and Omni 1.1 requests move to 1.2 on Dec. 3.

- Publisher: JARRUS (@jarrus.tech), thejarrus.com
- Story date: Nov. 5, 2026 (2026-11-05)
- Published: 2026-11-08
- Tags: Google, Image and video, Pricing and access
- URL: https://thejarrus.com/en/news/gemini-omni-1-2-flash/

### What changed

On Nov. 5, Google announced Gemini Omni 1.2 Flash, its video generation and editing model, and made it generally available in the Gemini API, Google Cloud and Gemini for business. Google says this is the first time Gemini Omni has been generally available, and it offers Provisioned Throughput for reserved enterprise capacity. The announcement was written by Anish Nangia, a product manager at Google DeepMind.

The model can generate and edit clips of **up to 15 seconds** in a single pass, up from 10 seconds with Omni 1.1. Length can be set in one-second steps from 3 to 15 seconds. According to the developer documentation, output runs at 24 frames per second in 360p, 720p, 1080p or 4K, with native audio. Interpolation between a first and last frame is capped at 10 seconds, and clips can be extended turn by turn to 30 seconds in total.

https://x.com/GoogleAI/status/2118389961426874879

### How the price works

Google says the price is 30% lower than Omni 1.1, at $0.07 per second of 720p video. The pricing page shows that billing is based on output tokens. Each second of 720p video counts as 5,792 tokens, and video output costs $12 per million tokens. Omni 1.1 charged $17.50 per million, or about $0.10 per second.

**Effective prices listed by Google**

- 10-second 720p clip: about $0.70; 15-second clip: about $1.04
- 360p: $0.023 per second
- 1080p with upsampling: $0.104 per second; 4K: $0.209 per second

Google suggests drafting at 360p or 720p and upscaling the best result. The model is offered only on the paid tier of the API. From Dec. 3, all requests to gemini-omni-1.1-flash will be routed automatically to 1.2 and billed at the new rates.

### References and conversational editing

Generation can be guided with character, product or style images, motion clips of up to three seconds and audio cues. Google says faces, garments, packaging text and brand colors hold steady across camera angles. Multi-turn edits, such as swapping a product or background or changing lighting, weather or aspect ratio, work across the full 15-second clip. The company also cites better lip-sync, distinct voices for multiple speakers and fewer unwanted jump cuts. Outputs carry an invisible SynthID watermark.

These claims come from Google's own announcement, which includes no independent or numerical benchmark. Google acknowledges that work continues on fast sports action, rapid script changes and complex physics.

### Where it is available

The model is also coming to Flow, Google Vids, the Gemini app, Google Ads and AI Studio. In the Gemini app, 15-second videos are opening up to Google AI Ultra subscribers. In Google Vids, anyone with a Google account or Workspace subscription can make **up to three** 15-second videos a month at no cost.

## Sources

1. [Google: Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips, Nov. 5, 2026](https://blog.google/innovation-and-ai/technology/developers-tools/introducing-gemini-omni-1-2-flash/)
2. [Google AI for Developers: Gemini Developer API pricing](https://ai.google.dev/gemini-api/docs/pricing)
3. [Google AI for Developers: Gemini Omni Flash](https://ai.google.dev/gemini-api/docs/models/gemini-omni-flash)
4. [Google: Generate longer AI videos with Omni 1.2 Flash in Google Vids at no cost., Nov. 5, 2026](https://blog.google/products-and-platforms/products/workspace/omni-1-2-flash-google-vids/)
5. [Google AI (X): Meet Gemini Omni 1.2 Flash ⚡️, Nov. 5, 2026](https://x.com/GoogleAI/status/2118389961426874879)
6. [Logan Kilpatrick (X): Today we are rolling out Gemini Omni Flash 1.2, Nov. 5, 2026](https://x.com/OfficialLoganK/status/2118390838434693281)

Report an error: corrections@thejarrus.com