Gemini Omni 1.2 Flash: 15-Second Video, 30% Lower Price
Longer 15-second clips, multi-turn editing and a $0.07-per-second 720p price headline Gemini Omni 1.2 Flash, now generally available.
Longer 15-second clips, multi-turn editing and a $0.07-per-second 720p price headline Gemini Omni 1.2 Flash, now generally available.
Introduction
On November 5, 2026, Google DeepMind product manager Anish Nangia announced on the Google blog that Gemini Omni 1.2 Flash is rolling out and is generally available across the Gemini API and Gemini for business. The release is an update to the Omni Flash video model, and Google's post compares it directly with Omni 1.1. The headline changes are native clips of up to 15 seconds, multi-turn conversational editing, stronger reference following, and a price Google says is 30% lower than Omni 1.1, at $0.07 per second for 720p video. Earlier Evermx coverage looked at the model's May debut and its July preview pricing; this review covers only what version 1.2 changes.
Feature Overview
What changed from Omni 1.1
| Item | Omni 1.1 Flash | Omni 1.2 Flash |
|---|---|---|
| Maximum clip length | 10 seconds | 15 seconds, set in one-second steps from 3 to 15 |
| Video output rate | $17.50 per 1M tokens | $12.00 per 1M tokens |
| Approximate 720p price | about $0.10 per second | about $0.07 per second |
| Video input for editing | up to 10 seconds | up to 15 seconds, with a 10-second lookback for extension |
| Resolutions | 360p, 720p, 1080p, 4K | 360p, 720p, 1080p, 4K |
| Frame rate | 24 FPS | 24 FPS |
The pricing and specification rows come from Google's Gemini API pricing and model pages. Resolution, frame rate and the 131,072-token input and 65,536-token output limits are unchanged between the two versions.
Capabilities Google highlights
Reference adherence. Generation can be guided by character, product or style images, short motion clips of up to three seconds, and audio cues. Google says faces, garments, packaging typography and brand colors stay consistent across camera angles. The Gemini API video guide says character consistency works across up to 6 reference images.
Consistency. Google describes less visual drift or morphing from first to last frame, including when interpolating between a first and last keyframe or extending a clip. Its post includes a side-by-side example in which Omni 1.1 does not match a reference poster as closely as 1.2.
Multi-turn editing. A clip can be refined turn by turn, for example by swapping a product or background, changing lighting or weather, or switching the aspect ratio, and Google says this works across full 15-second clips. The model page says refinement and editing run through the Interactions API.
Speech and camera control. Google lists more natural dialogue, clearer lip-sync and multi-speaker conditioning, plus continuous camera moves such as FPV flythroughs, zoom-outs and orbits with fewer unwanted jump cuts.
Pricing by resolution
Video is billed on output tokens. At $12.00 per million output tokens, the pricing page lists the following per-second costs.
| Resolution | Output tokens per second | Approximate price per second |
|---|---|---|
| 360p | 1,931 | $0.023 |
| 720p | 5,792 | about $0.07 |
| 1080p (with upsampling) | 8,688 | $0.104 |
| 4K (with upsampling) | 17,376 | $0.209 |
The page puts a 10-second 720p clip at about $0.70 and a 15-second clip at about $1.04. Google's suggested workflow is to draft at 360p or 720p, fix details with follow-up edits instead of regenerating, and upscale only the best results to 1080p or 4K.
Usability Analysis
Availability is broad. Google's post lists the Gemini API through Google AI Studio, the Google Cloud console and API for businesses (with Provisioned Throughput available), Flow for multi-turn edits, Google Vids, the Gemini app, and Google Ads. In Google Vids, 15-second clips come at no additional cost with a Google account or Google Workspace subscription. In the Gemini app, 15-second videos are rolling out to Google AI Ultra subscribers.
For developers, the pricing page states the model is on the paid tier of the Gemini API and not on the free tier. It lists a single Standard tier, and both Omni versions use the same input rate of $1.50 per million tokens for text, image and video. The migration detail matters for anyone already integrated: from December 3, 2026, requests to gemini-omni-1.1-flash automatically route to gemini-omni-1.2-flash and are billed at 1.2 rates. Teams that pinned 1.1 for visual comparisons should test against 1.2 before that date, because the output will change.
The cost structure suits iteration. Cheap low-resolution drafts followed by conversational edits keep the expensive upscale for the final pass, though the post does not give a measured cost for a typical edit session.
Pros and Cons
Pros:
- Longer clips of up to 15 seconds, up from 10 in Omni 1.1
- Lower video output rate, $12.00 versus $17.50 per million tokens
- Multi-turn editing avoids regenerating a whole clip for a small change
- Broad availability across Google's API, cloud, creative and consumer products
- Outputs carry an imperceptible SynthID watermark
Cons:
- Paid-tier access only on the Gemini API, with no free tier
- Google says work continues on fast sports action, rapid script changes and complex physics
- Quality claims are shown through example clips rather than benchmark scores
- 1080p and 4K output is priced higher, at $0.104 and $0.209 per second
Outlook
Per the pricing page, requests to Omni 1.1 route to 1.2 from December 3, so after that date 1.1 requests are served by 1.2. The model page also lists the earlier gemini-omni-flash-preview as shut down, and the video guide says Veo 3.1 Preview models in the Gemini API were scheduled to shut down on October 22, 2026, recommending a move to Omni Flash or to the generally available Veo 3.1 models offered through the Gemini Enterprise Agent Platform. Developers still calling earlier video models in the API should check these dates against their own integrations.
Google's own list of weak spots, fast sports action, rapid script changes and complex physics, is a useful checklist for evaluators. Longer clips raise the stakes for those cases, because errors have more seconds in which to appear.
Conclusion
Gemini Omni 1.2 Flash is a measured version update. It lengthens clips, lowers the per-token price and improves editing and reference control, while leaving resolution, frame rate and token limits unchanged. Product marketers, ad teams and developers building video features on the Gemini API are the clearest audience, particularly those who value editing a clip over regenerating it. Teams should verify the reference and consistency claims on their own assets, since the evidence in the announcement is Google's example clips.
Editor's Verdict
Gemini Omni 1.2 Flash: 15-Second Video, 30% Lower Price earns a solid recommendation within the Gemini space.
The strongest case for paying attention: longer clips of up to 15 seconds, up from 10 in Omni 1.1. That alone raises the bar for what readers should expect in this space. Reinforcing that, lower video output rate of $12.00 versus $17.50 per million tokens — practical value rather than just headline appeal. The broader signal worth registering is straightforward: clip length and price moved together in this release, with maximum duration rising from 10 to 15 seconds while the video output rate fell from $17.50 to $12.00 per million tokens. On the other side of the ledger, one constraint is real rather than a marketing footnote: paid-tier access only on the Gemini API, with no free tier. It should factor into any serious decision. Layered on top of that, Google says work continues on fast sports action, rapid script changes and complex physics — which narrows the set of teams for whom this is an obvious yes.
For Google Cloud and Workspace integrators, multimodal-first teams, and Gemini API adopters, this is a serious evaluation candidate, not just a curiosity to bookmark. For everyone else, the safer posture is to monitor coverage and revisit once the use cases that matter to your team are demonstrated in the wild.
Pros
- Longer clips of up to 15 seconds, up from 10 in Omni 1.1
- Lower video output rate of $12.00 versus $17.50 per million tokens
- Multi-turn editing avoids regenerating a whole clip for a small change
- Broad availability across Google's API, cloud, creative and consumer products
- Outputs carry an imperceptible SynthID watermark
Cons
- Paid-tier access only on the Gemini API, with no free tier
- Google says work continues on fast sports action, rapid script changes and complex physics
- Quality claims are shown through example clips rather than benchmark scores
- Upscaled 1080p and 4K output costs more, at $0.104 and $0.209 per second
References
Comments0
Key Features
Gemini Omni 1.2 Flash (gemini-omni-1.2-flash), announced November 5, 2026: clips of 3 to 15 seconds (10 seconds in Omni 1.1), multi-turn conversational editing, stronger reference adherence and consistency, and video output at $12.00 per 1M tokens (about $0.07 per second at 720p, versus $17.50 per 1M tokens in 1.1). 360p to 4K output at 24 FPS. Available on the paid Gemini API tier, Google Cloud, Flow, Google Vids, Google Ads, and the Gemini app for Google AI Ultra subscribers.
Key Insights
- Clip length and price moved together in this release, with maximum duration rising from 10 to 15 seconds while the video output rate fell from $17.50 to $12.00 per million tokens
- Multi-turn editing is aimed at lowering total cost, since a follow-up edit replaces regenerating the whole clip
- Resolution, frame rate and token limits are unchanged from Omni 1.1, so the gains are in duration, control and price rather than output format
- From December 3, 2026, requests to gemini-omni-1.1-flash route to 1.2 and are billed at 1.2 rates, so existing integrations will change output automatically
- Google's post lists fast sports action, rapid script changes and complex physics as areas still being improved
- Reach is broad across the Gemini API, Google Cloud, Flow, Google Vids, Google Ads and the Gemini app, though the Gemini app rollout starts with Google AI Ultra subscribers
- The announcement's quality claims rest on example clips, including a side-by-side with 1.1, rather than published benchmark scores
Was this review helpful?
Share
Related AI Reviews
Google AI Mode Adds Temporary Threads for Private Queries
Google's AI Mode in Search gets temporary threads: sessions detached from your account, not saved to history or used for personalization.
Gemini Tasks Goes Free: AI Calls, Payments, Hydrogen Model
Google makes Tasks in Gemini free in six countries on Gemini 4 Hydrogen; U.S. users add business calls, AP2 checkout and email or text intake.
Google Ask Maps Adds Trip Itineraries, Appointment Finding
Google's Ask Maps now builds day-by-day itineraries, adds route tips, finds appointments by calling businesses, and expands to 30 European countries.
Gemini 4 Hydrogen: Fast Model, Four Thinking Levels
Google's Gemini 4 Hydrogen targets everyday coding and agents at $1.50/$7.50 per million tokens, with four thinking levels and wide rollout.
