# Google releases Gemini Omni 1.2 Flash: 15-second videos and lower pricing

> Google launches Omni 1.2 Flash with videos up to 15 seconds, conversational editing and 30% lower 720p video pricing. Demos, costs and availability.


Published: 2026-11-05. Original source: [Google Cloud · Gemini Omni 1.2 Flash, general availability](https://cloud.google.com/blog/products/ai-machine-learning/gemini-omni-1-2-flash-generally-available).

![Official Google Cloud artwork introducing Gemini Omni 1.2 Flash, with scenes of bees, animated characters, a woman in a city and an octopus.](/news/omni12-flash/official-cover.jpg)

Official artwork from [Google Cloud's announcement](https://cloud.google.com/blog/products/ai-machine-learning/gemini-omni-1-2-flash-generally-available). 

**Google has released Gemini Omni 1.2 Flash**, its model for generating and editing video with audio. The November 5 release supports scenes up to **15 seconds**, closer reference consistency, and conversational editing. Google announces **$0.07 per second of 720p video**, 30% less than Omni 1.1 Flash. [Official announcement](https://cloud.google.com/blog/products/ai-machine-learning/gemini-omni-1-2-flash-generally-available).

For someone making ads or product videos, the proposition is concrete: generate a longer scene and keep working on it. You can request another camera angle, change the lighting, or swap a product through follow-up instructions. Google presents more stable products, characters, and brand details as an improvement; HeyMark has not independently measured that claim.

## What changes from Omni 1.1 Flash

- **Longer clips:** generation and editing from 3 to 15 seconds, up from 1.1's 10-second maximum. Interpolation between a first and last frame keeps a 10-second limit.
- **Multi-turn editing:** refine the same clip in a conversation, with changes such as camera angle or lighting.
- **Less visual drift, according to Google:** closer adherence to image and video references helps preserve details.
- **Native audio:** the announcement highlights more natural dialogue, lip-sync, and distinct speakers. Audio references require allowlisted access.
- **Drafts and finishing:** 360p and 720p options, with upscaling to 1080p or 4K.

Sources: [Gemini API model card](https://aistudio.google.com/docs/models/gemini-omni-flash) and [Google Cloud announcement](https://cloud.google.com/blog/products/ai-machine-learning/gemini-omni-1-2-flash-generally-available).

## Watch the launch demonstrations

Google includes examples from its partners. These are the demonstrations from **FLORA**, focused on editing and changes of style, and **Photoroom**, which uses the model in its product-video tools. They are selected launch samples: useful for seeing the kind of output being shown, rather than establishing a success rate.

![FLORA demonstration included in Google Cloud's announcement](/news/omni12-flash/flora-poster.jpg)

[Watch the FLORA demonstration on YouTube](https://www.youtube.com/watch?v=Opx8Uf6vcqg).

![Photoroom demonstration included in Google Cloud's announcement](/news/omni12-flash/photoroom-poster.jpg)

[Watch the Photoroom demonstration on YouTube](https://www.youtube.com/watch?v=fwTIGK0ODiU).

If you try it with your brand's product, comparing the object before and after an edit still matters: logo, shape, color, and continuity. An attractive demo does not replace checking the piece you will deliver to a client.

## What a clip costs

The [Gemini API Standard rate](https://aistudio.google.com/docs/pricing#gemini-omni-1.2-flash) is **$12 per million output video tokens**, down from $17.50 for 1.1. At 720p, output uses 5,792 tokens per second; the announcement's $0.07/s is rounded.

**Cost per clip · 720p · USD**

| Duration | Omni 1.2 Flash | Omni 1.1 Flash |
| --- | ---: | ---: |
| 5 s | $0.35 | $0.51 |
| 10 s | $0.70 | $1.01 |
| 15 s | $1.04 | Not available: 10s maximum |

Includes 720p output video only. Input and text are billed separately.

[Official rates](https://aistudio.google.com/docs/pricing#gemini-omni-1.2-flash)

Calculation: seconds × 5,792 × rate per million ÷ 1,000,000, rounded to cents. Standard input is $1.50 per million text, image, or video tokens; output text is $9 per million. Another edit can produce additional billable output. [Pricing and conditions](https://aistudio.google.com/docs/pricing#gemini-omni-1.2-flash).

## Where it is available

Omni 1.2 Flash is generally available on **Google Cloud** and the **paid tier of the Gemini API**, under `gemini-omni-1.2-flash`. Google points business users to Google Vids and says it is **coming soon to Gemini for business**. That distinction matters when checking whether a particular chat plan already includes it. [Announced availability](https://cloud.google.com/blog/products/ai-machine-learning/gemini-omni-1-2-flash-generally-available).

Developers have another date to watch: **from December 3, 2026**, Gemini API requests to `gemini-omni-1.1-flash` will route to 1.2 and use its rates. If your integration uses the previous model, review that transition and test the results before the date. [Versions and migration](https://aistudio.google.com/docs/models/gemini-omni-flash).

## Plan your next post in HeyMark.

Keep the idea, review the draft with your team, and see how it performed in the accounts you connected.

[Start free](https://app.heymark.ai) · [See how it works](https://heymark.ai/en/#product)

## Developer and agent resources

- [HeyMark MCP documentation](https://heymark.ai/en/mcp/)
- [llms.txt](https://heymark.ai/llms.txt)
- [Full site content for language models](https://heymark.ai/llms-full.txt)
- MCP protocol endpoint: `POST https://mcp.heymark.ai`
- OAuth protected-resource metadata: [/.well-known/oauth-protected-resource](https://mcp.heymark.ai/.well-known/oauth-protected-resource)
- MCP server card: [/server-card](https://mcp.heymark.ai/server-card)