Skip to content
Models · Nov 5, 2026

Gemini Omni 1.2 Flash launches with 15-second video generation, 30% lower cost, and multi-turn editing

The updated model reduces pricing to $0.07 per second for 720p video, supports clips up to 15 seconds, and improves reference adherence and conversational editing across the Gemini API and Google Vids.

Trust84
HypeLow hype

1 source · cross-referenced

ShareXLinkedInEmail
TL;DR
  • Gemini Omni 1.2 Flash introduces native 15-second video generation, up from 10 seconds in the prior version.

Google DeepMind announced the general availability of Gemini Omni 1.2 Flash, a model update that adds native support for 15-second video clips, up from the 10-second limit in Omni 1.1. The update also reduces pricing by 30%, bringing the cost to $0.07 per second for 720p video.

The new model improves reference adherence, allowing users to combine character, product, or style images, short motion clips (up to three seconds), and audio cues to guide generation. Faces, garments, packaging typography, and brand colors are maintained consistently across camera angles, enabling use cases like virtual try-on sequences and branded video ads.

Gemini Omni 1.2 Flash introduces multi-turn conversational editing, enabling users to refine clips iteratively without restarting from scratch. Edits such as swapping products, changing backgrounds, adjusting lighting, or switching aspect ratios can be applied turn by turn across full 15-second clips.

The model is generally available on the Gemini API and Google Cloud, and is also integrated into Google Vids and Gemini for Business for scalable video production.

Sources
  1. 01Google DeepMind — Blog — Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips
Also on Models

Stories may contain errors. Dispatch is assembled with AI assistance and curated by human editors; despite the trust-score filter, mistakes happen. We correct publicly — every article links to its revision history. Nothing here is financial, legal, or medical advice. Verify before relying on any claim.

© 2026 Dispatch. No ads. No sponsorships. No paid placement. Reader-supported via Ko-fi.

Built by a person who cares about honest AI news.