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

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.

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 and Google Cloud announcement.

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.

Play demonstration ▶

Watch the FLORA demonstration on YouTube.

Play demonstration ▶

Watch the Photoroom demonstration on YouTube.

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 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 clip720p · USD

720p output video cost comparison, in US dollars

Duration	Omni 1.2Flash	Omni 1.1Flash
5 s	$0.35	$0.51
10 s	$0.70	$1.01
15 s	$1.04	—10s maxNot available for 15 seconds

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

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.

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.

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.