🔍 Read the full analysis: Gemini Omni 1.2 Flash Offers A Faster, More Affordable AI Workflow on ThorstenMeyerAI.com
Get the latest gadgets delivered free with Prime
- Fast, free delivery on millions of items
- Prime Video, Amazon Music and more included
- Member-only deals all year
TL;DR
Google announced Gemini Omni 1.2 Flash on Nov. 5, adding video generation and editing for clips up to 15 seconds and setting the 720p price at $0.07 per second. Google says that rate is 30% lower than version 1.1, but the announcement did not include independent performance tests or prices for other resolutions.
Google announced Gemini Omni 1.2 Flash on Nov. 5, adding generation and editing for video clips up to 15 seconds and setting the 720p price at $0.07 per second. The company says that rate is 30% below Gemini Omni 1.1 and that the new model is generally available through the Gemini API and Gemini for business, with rollout also beginning across other Google products.
Google says users can choose clip lengths in one-second increments from three to 15 seconds, up from the 10-second maximum it attributed to version 1.1. The company also describes a multi-turn editing workflow: users can request changes in follow-up prompts, such as replacing a background or adjusting lighting, instead of generating the entire clip again.
The stated $0.07-per-second rate applies to 720p video. Google says users can draft at 360p or 720p and upscale selected clips to 1080p or 4K, but the announcement supplied no prices for those resolutions or for upscaling. Developers can prototype through Google AI Studio. Google also lists availability in Flow and Google Vids, without a schedule for access on each platform.
Google says the model can use reference images, motion clips of up to three seconds and audio cues. The company claims improvements in reference following, continuity of characters and products, speech, lip-sync and camera movement. It says generated outputs carry an imperceptible SynthID watermark and that Provisioned Throughput is available. These are Google’s product descriptions; the announcement did not provide independent evaluations or standardized comparisons.
Gemini Omni 1.2 Flash Longer clips, lower stated cost
Google’s update brings longer video generation and conversational editing. Its price and quality claims still need independent evaluation.
What changes for creators
The update targets short video workflows that need multiple versions and revisions.
More room for a scene
The maximum rises from 10 to 15 seconds, with duration selectable in one-second increments.
Revise with prompts
Users can request changes such as a new background or lighting adjustment without regenerating the whole clip.
Guide the generation
Google says the model can use reference images, motion clips up to three seconds, and audio cues.
Where it is rolling out
Google says access is beginning across its products and developer platforms.
What the price covers
The announced rate applies to 720p video; other resolution and upscaling costs were not provided.
Google says creators can choose either resolution for drafts.
The stated $0.07-per-second rate is for 720p video.
Selected clips can be upscaled to 1080p or 4K, but those prices were not stated.
Claims awaiting testing
Google describes improvements, but the announcement supplies no independent benchmarks or standardized comparisons.
- Better reference following and continuity
- Improvements to speech, lip-sync, and camera movement
- Edits can preserve scene details across changes
- Reliability across varied scenes and demanding footage
- Failure rates and time saved in real workflows
- Total cost, including higher resolutions and upscaling
Lower Costs for Short Video Work
The combination of a 15-second limit, follow-up editing and a lower stated 720p rate could matter to teams producing short ads, explainers and social videos. If edits preserve the existing scene as Google describes, creators may be able to make variations without starting over each time. The lower per-second rate may also be relevant to developers or businesses generating many clips.
Those potential savings are not yet quantified. The announcement does not say how often the model preserves requested details during revisions, how much time editing saves, or what the total cost becomes when users upscale output. The 30% price reduction is specifically a comparison with Gemini Omni 1.1, not with competing video services. Actual value will depend on output quality, revision needs and the full cost of a workflow.
Products Worth Considering
Jackery Explorer 1000 v2 Portable Power Station
Bose SoundLink Max Portable Bluetooth Speaker, IP67 Waterproof, Black
EcoFlow DELTA 3 Max Portable Power Station, 2048Wh LFP Battery
As an affiliate, we earn on qualifying purchases.
What Changed From Version 1.1
Google says Gemini Omni 1.1 generated clips up to 10 seconds. Version 1.2 Flash raises that stated ceiling to 15 seconds and adds conversational editing for clips of that length. The company presents those changes alongside claimed improvements to reference adherence, continuity and speech generation.
Google’s announcement includes intended-use examples such as virtual try-on sequences, animated product posters and scenes with multiple speaking characters. Those examples show the kinds of work the company is targeting, but they do not establish how the model performs across real projects. Google also says development is continuing on fast sports action, rapid script changes and complex physics, identifying areas where further work remains.
““Gemini Omni 1.2 Flash introduces native 15-second video creation, multi-turn conversational editing capabilities, and enhanced reference following.””
— Google DeepMind, in its Nov. 5 product announcement
Performance and Pricing Still Open
The announcement did not include independent benchmarks, a detailed testing method or comparative failure rates for the claimed gains in reference following, continuity and lip-sync. It is not yet clear how reliably the model handles demanding footage, including fast movement, complex interactions or requests that change rapidly. Google’s statement that work continues in several of those areas signals that performance may vary by task.
Pricing beyond 720p also remains unspecified: Google did not give rates for 360p, 1080p or 4K, or explain how upscaling is billed. The company said rollout is beginning across its products and developer platforms, but did not provide a region-by-region or account-by-account schedule. Without those details, users cannot yet calculate the full cost or know when a particular product will provide access.
Rollout and Independent Testing
Google says Gemini Omni 1.2 Flash is rolling out through the Gemini API and Gemini for business, with the announcement also pointing to Google AI Studio, Flow and Google Vids. The company has not supplied dates for access on each platform. Developers and businesses will be able to test the new clip limit and editing workflow as access reaches their accounts.
The next useful evidence will be testing across varied footage that reports both quality and failure rates, alongside clearer pricing for higher resolutions and upscaling. Google says it will continue work on fast action, rapid script changes and complex physics, but announced no dates for those improvements. For now, the feature limits and 720p price are the specific terms Google has stated; the practical scale of its performance gains remains to be established.
Key Questions
What is Gemini Omni 1.2 Flash?
It is Google’s AI video model for generating and editing clips. Google says it supports clips up to 15 seconds and follow-up prompt-based edits.
How much does 720p video cost?
Google lists a price of $0.07 per second for 720p video and says that is 30% below the price of Gemini Omni 1.1. The announcement does not state prices for other resolutions.
Where is the model available?
Google says it is generally available through the Gemini API and Gemini for business, with rollout beginning across other products, including Flow and Google Vids. It did not provide a schedule for every platform or account.
Has its video quality been independently tested?
The supplied announcement contains no independent benchmarks or standardized comparisons. Claims about reference following, continuity, speech and lip-sync are Google’s product claims.
Can users edit a clip without generating it again?
Google says users can request changes through follow-up prompts, including changes to a background or lighting. The announcement does not quantify how reliably those edits preserve other details in a scene.
Primary source: Google AI · via ThorstenMeyerAI.com
