AboutAI ToolsCursorClaude CodeLovableBolt.newAI tool reviewsTutorialsVibe codingAI agentsMobile apps with AIAll tutorialsBlogSponsorWork With MeJoin 285K+ Subscribers

5 November 2026 · 3 min read

Gemini Omni 1.2 Flash Now GA: 15-Second Clips and 30% Lower Price

Google has made Gemini Omni 1.2 Flash generally available, bringing 15-second video generation, conversational editing, and a 30% price cut to $0.07 per second for 720p.

On 5 November 2026, Google made Gemini Omni 1.2 Flash generally available across the Gemini API and Gemini for business [1][4]. The model is designed for the kind of video businesses produce in volume — product spins, try-on clips, social ads — and it comes with a set of changes that target cost, consistency, and creative control.

What’s new

Longer clips. The maximum clip length rises from 10 seconds to 15 seconds, and developers can specify any duration from 3 to 15 seconds in one-second increments [1][2][4]. A 15-second ceiling means a full product explainer or a complete social ad spot can be generated in a single pass.

Lower price. The cost for 720p video drops 30% to $0.07 per second [1][2][3]. Google states that comparable savings apply at other resolutions, though only the 720p figure is confirmed [1]. At the new rate, a 15-second clip costs $1.05; a hundred such clips cost $105 [2]. The previous Omni 1.1 Flash price was not restated in the announcement, but arithmetic based on the 30% reduction suggests it was roughly $0.10 per second [2].

Conversational editing. Users can refine the same clip turn by turn — swapping a product, changing lighting or weather, or switching the aspect ratio — instead of starting over [1][3][4]. This multi-turn editing works across the full 15-second length and is intended to reduce the number of paid regenerations needed to land a usable result [2][3].

Better reference adherence. The model accepts character images, product photos, short motion clips (up to three seconds), and audio cues, and keeps faces, garments, packaging typography, and brand colours consistent across camera angles [1][4]. Consistency is said to hold across up to six reference images [2]. Audio references are gated behind allowlisting [1].

More consistent results. Google reports less visual drift or morphing across motion and camera transitions, and stronger first-to-last-frame consistency when interpolating or extending clips [4].

Natural speech and cinematic control. The model can generate scenes with more fluid dialogue, clearer lip-sync, and distinct multi-speaker conditioning [1][4]. It also handles complex continuous camera movements — such as FPV drone flythroughs or dramatic zoom-outs — with fewer unwanted jump cuts [3][4].

Availability and pricing

Gemini Omni 1.2 Flash is available through the Gemini API (model ID gemini-omni-1.2-flash), Google AI Studio, the Google Cloud Console, Flow, Google Vids, the Gemini app for Google AI Ultra subscribers, and Google Ads [3][4]. Provisioned Throughput is offered, and all outputs carry an imperceptible SynthID watermark [1][4].

The primary billing metric is per-second video generation. Drafts can be created at 360p or 720p, then upscaled to 1080p or 4K [1][3]. Token-based pricing also appears in the API release notes at $12.00 per 1 million tokens, but the sources do not specify which token class that figure covers [2]. Developers should confirm which meter applies to their usage.

What it means for developers

For teams building video into products or ad workflows, the combination of longer clips, per-second billing, and conversational editing changes the cost equation. Drafting at lower resolution and editing in conversation can cut the number of full-price generations needed to reach a final clip [3]. The improved reference adherence makes it easier to turn existing product photos or character sheets into consistent video sequences without manual frame-by-frame correction [1][4].

Google positions the model as production-ready, backed by enterprise infrastructure, and already integrated into tools from partners such as Photoroom, Artlist, invideo, Picsart, and Runway [1][4]. The company also notes ongoing work to improve fast sports action, rapid script changes, and complex physics [4].

Sources

  1. Gemini Omni 1.2 Flash now GA: cost-effective video | Google Cloud Blog
  2. Gemini Omni 1.2 Flash GA: $0.07/Sec, 15s Video [2026]
  3. Google's Gemini Omni 1.2 Flash stretches AI video clips to 15 seconds and cuts pricing by 30 percent
  4. Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips
  • gemini omni
  • video generation
  • google cloud
  • ai video
  • gemini api

Researched and drafted with AI from the sources above.

Learn to build with AI

Hands-on tutorials on Cursor, Claude Code, AI agents and more.