Skip to content
Images & videomedium signalverified

Gemini Omni 1.2 Flash cuts 720p video to about $0.07 per second and extends clips to 15 seconds

Google made the video model generally available on November 5, 2026, through the Gemini API and Gemini for business. It says the price is 30% below Omni 1.1. Clips can now run from 3 to 15 seconds in one generation, and the free tier does not include the model.

By Redakcija WebAiRadarPublished 1 min readwritten by a model
Image: Google

Google has released Gemini Omni 1.2 Flash, a model that generates and edits video, at about $0.07 per second of 720p footage. Google says that is 30% below Omni 1.1. For anyone producing short video through the API, the release changes both the bill and the length of what one request can return.

One generation can now produce between 3 and 15 seconds of video, set in one-second steps, compared with a 10-second ceiling on Omni 1.1. A clip can also be changed through follow-up instructions, such as a new background or aspect ratio, instead of being generated again from the start. Google suggests drafting at 360p or 720p, fixing details with a follow-up edit, and enlarging only the best result to 1080p or 4K. The Gemini API price list sets a separate rate per second for each resolution, and the model is available only on the paid tier.

What Google claims for consistency

Google says the model holds faces, garments, and packaging typography more steadily across camera angles. It accepts images, motion clips of up to three seconds, and audio cues as references. Google also reports clearer lip-sync and fewer unwanted jump cuts. These are the company's own descriptions, and the announcement cites no independent measurement of them.

BrandsGemini

Once a week, in your inbox

The whole week's news, gathered into one email. No ads, no passing your address on, one-click unsubscribe.

The address is used only for this roundup. It is not sold and not passed to anyone.

Related

Three phone screens from OpenAI's demo of the ChatGPT try-on: a product page for a denim pleated skirt with a Try on button, a selfie being taken with the camera, and the generated image of the same woman wearing the skirt.
Images & videomedium signal

ChatGPT adds virtual try-on for clothes and keeps your reference photo for later

OpenAI added two shopping features to ChatGPT on October 1, 2026. A Try on button on listings for clothes and accessories generates an image of the item on you from a selfie. The selfie is saved as a reference photo for future try-ons until you change or delete it in settings. A second feature, Favorites, saves products to your ChatGPT Library.

OpenAIverified

Images & videomedium signal

Gemini 3.8 Live can now answer as a talking video avatar, and Google bills the video only while it speaks

Google made Gemini 3.8 Live with Live Avatar generally available in Gemini Enterprise on September 24, 2026, with US and EU endpoints. The model replies through a lip-synced video character while it listens, watches a camera or a shared screen, and calls tools in the background. Avatar video costs $1 per million tokens at 6,192 tokens for each second of speech. By our arithmetic, that comes to about $0.37 per spoken minute before audio, input, and context charges.

Googleverified