How much does Gemini Omni 1.2 Flash cost?
Google has made its Gemini Omni 1.2 Flash video model generally available, opening it to developers and businesses through the Gemini API and Gemini for business. The company says the model can now create and edit videos up to 15 seconds long natively, and it has cut the price by 30 percent from the previous version. For 720p video, the cost is $0.07 per second.
What is new in Gemini Omni 1.2 Flash?
The longer runtime is the most visible change. Omni 1.1 topped out at 10 seconds. Users can now specify any length from 3 to 15 seconds, in one-second increments, which Google says gives creators room to tell a complete story, build a product explainer or produce a full social ad in a single generation.
Google is also pitching a cheaper workflow. Users can draft at 360p or 720p, fix a detail with a follow-up edit rather than regenerating the whole clip, and then upscale the best results to 1080p or 4K. That approach, the company argues, keeps costs down for teams producing videos at scale.
Can Gemini Omni 1.2 Flash keep products consistent across camera angles?
The model handles reference material more closely than its predecessor. Users can guide generation with character, product or style images, short motion clips of up to three seconds, and audio cues. Google says faces, clothing, packaging text and brand colors stay consistent across camera angles, which makes it possible to turn existing product photos or character sheets into virtual try-on clips, catalog spins and branded video ads. In one example Google published, a single model photo combined with front-and-back shots of three outfits produced a 15-second try-on sequence with 360-degree turns while keeping each garment's cut and drape intact.
Editing is now conversational. Instead of rebuilding a clip from scratch, users can refine it turn by turn, swapping a product or background, changing the lighting or weather, or switching the aspect ratio. Google says the multi-turn editing works across full 15-second clips, which makes it easier to produce ad variants for different audiences and placements. In one demonstration, a single clip had its background changed several times, from a striped pavilion tent to an oak forest, a stable, a market fair and a stone castle, while the characters' performances and the camera framing held steady.
Speech has also been upgraded. Google says the model produces more fluid dialogue, clearer lip-sync and distinct voices for multiple speakers. That applies whether users are directing multi-character scenes in Flow, building video explainers in Gemini for business, or making videos with avatars, music and narration in Google Vids.
Camera control is another focus. The company says the model can handle sweeping first-person drone flights, dramatic zoom-outs and orbiting shots with significantly fewer unwanted jump cuts and a steadier sense of scale. Google's example used two architectural reference photos to generate a single continuous drone flight across a piazza, through bronze doors and up into the dome of the Pantheon, with no cuts.
Google is positioning the model for commercial use. Gemini Omni is now generally available and backed by Google Cloud's enterprise infrastructure and security. Provisioned Throughput is available for customers who need reserved capacity, and all outputs carry an imperceptible SynthID watermark.
Google acknowledged some limits. The company said development is ongoing to improve fast sports action, rapid script changes and complex physics.
The model is available across several Google products. Developers can prototype in Google AI Studio, explore starter apps and review the developer documentation and pricing. Businesses can try it in the Google Cloud console and build enterprise solutions through the API. Users of Google's consumer and productivity tools will find it in several places. Flow supports scene direction and multi-turn edits. Google Vids offers 15-second clips at no additional cost to people with a Google account or a Google Workspace subscription. The Gemini app can create 15-second videos, though that feature is rolling out first to Google AI Ultra subscribers. Google Ads can use the model to scale video campaigns.
Este artículo fue escrito con la asistencia de IA.
News Factory APP - noticias agénticas para impulsar tu SEO y AEO.