All postsSHORT3 min read
Gemini Omni 1.2 Flash: A 15-Second AI Ad for About $1
Google's Gemini Omni 1.2 Flash makes 15-second video clips with native audio for $0.07 a second at 720p. What changed, the catch, and how to use it.
Google's AI video model can now make a whole 15-second clip, with sound, in one generation. On the Gemini API that's about $1.04 at 720p. Gemini Omni 1.2 Flash went generally available on November 5, 2026, and the price per second dropped 30% at the same time.
What changed
Google announced Gemini Omni 1.2 Flash on its blog and in the Gemini API changelog on November 5, 2026, and made it generally available on the Gemini API and Google Cloud. The headline changes:
- Longer clips. Videos now run up to 15 seconds, up from 10 with Omni 1.1. You can pick any length from 3 to 15 seconds in one-second steps. Google pitches the extra time for "complete stories," "product explainers" and "full social ad spots in a single generation."
- Lower price. $0.07 per second of 720p video, 30% less than Omni 1.1 Flash (which the pricing page puts at about $0.10 per second).
- Native audio. The model card lists the output as "Video with native Audio." Google also says dialogue and lip-sync got more natural.
- Editing in conversation. You can refine the same clip turn by turn: swap a product or background, change the lighting, or switch the aspect ratio, instead of starting over.
- Better reference following. You can guide it with character, product or style images, short motion clips (up to three seconds) and audio cues. Google says faces, garments, packaging typography and brand colors stay consistent across camera angles. Audio references are gated behind allowlisting, per the Google Cloud post.
The model ID is gemini-omni-1.2-flash. Output comes in 360p, 720p, 1080p or 4K at 24 FPS, and you can extend a clip 3 to 10 seconds per turn, up to 30 seconds total.
The math, and the catch
The pricing page bills video output at $12 per million tokens, at 5,792 tokens per second of 720p video. That's about $0.70 for a 10-second clip and $1.04 for a 15-second one.
Some fine print before you plan around that dollar:
- It's the 720p price. Google's suggested workflow is to draft at 360p or 720p, fix details with follow-up edits, then upscale your best clips to 1080p or 4K.
- No free API tier. The pricing page lists the free tier as "Not available" for this model. It's on the paid tier of the Gemini API. Google says Google Vids can generate 15-second clips at no additional cost with a Google account or Workspace subscription, and 15-second videos in the Gemini app are rolling out to Google AI Ultra subscribers.
- Every clip is watermarked. Outputs carry an imperceptible SynthID watermark.
- Known weak spots. Google says it's still improving "fast sports action, rapid script changes and complex physics."
- Omni 1.1 is going away. From December 3, 2026, requests to
gemini-omni-1.1-flashare routed to 1.2 and billed at 1.2 rates.
Google's quality claims, and the partner quotes and examples in the Cloud post (Artlist, FLORA, invideo, Krea, Picsart, Runway, Photoroom, QuickFrame AI), come from the companies themselves. I haven't tested the model for this post.
Try it
- Open Google AI Studio with a paid Gemini API project and pick
gemini-omni-1.2-flash. - Upload one product photo as a reference and ask for a 15-second clip at 720p.
- In the same conversation, ask for one change, like a new background or a vertical aspect ratio.
- Write down how many turns it took to get a clip you'd post. Your real cost per finished ad is roughly turns × seconds per turn × $0.07 at 720p, plus input tokens ($1.50 per million).
Here's how you get paid
My opinion, no income guaranteed: many small shops have product photos but no video. Sell them a pack of 15-second product ads:
- Their photos in. Use the shop's own product shots as references. Google says packaging typography and brand colors stay consistent across camera angles, but check each clip.
- Ads out. A 15-second ad per product, drafted at 720p, with only the keepers upscaled.
- One edit per placement. Use a follow-up edit to switch the aspect ratio or swap the background for each placement. Each edit turn is billed, so count it in your price.
Check every clip yourself before it ships, and tell the client the videos carry Google's SynthID watermark.
Daily email
Get each breakdown in your inbox.
One email each evening, right after the Short goes live: the AI tool it covers, the full write-up with sources, and how to get paid for it. Free, and you can unsubscribe anytime.
Sources
- Google blog, "Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips" (November 5, 2026): https://blog.google/innovation-and-ai/technology/developers-tools/introducing-gemini-omni-1-2-flash/
- Google Cloud blog, "Gemini Omni 1.2 Flash ... now generally available" (November 5, 2026): https://cloud.google.com/blog/products/ai-machine-learning/gemini-omni-1-2-flash-generally-available
- Gemini API pricing: https://ai.google.dev/gemini-api/docs/pricing
- Gemini API changelog: https://ai.google.dev/gemini-api/docs/changelog
- Gemini Omni Flash model card: https://ai.google.dev/gemini-api/docs/models/gemini-omni-flash