Tech Meridian← ALL MODELS
PROMY MERIDIAN

GOOGLE DEEPMIND · MODEL RELEASE TRACKER

Gemini Omni 1.2 Flash

Gemini Omni 1.2 Flash is a video-generation and editing model from Google DeepMind that generates native video clips up to 15 seconds, adds multi-turn conversational editing, stronger reference-following and consistency, and is offered at reduced pricing and broad availability across Google products and APIs.

CURRENT SNAPSHOT4/5 DIMENSIONS WITH DATA

The dimensions that change the decision.

PRICING
Pricing (720p)Price reduced 30% from Omni 1.1; available at $0.07 per second for 720p video.
CONTEXT WINDOW
Maximum generated clip durationGenerates and edits native videos up to 15 seconds long; duration can be specified in one-second increments from 3 to 15 seconds.
MODALITIES
Input modalities and output improvementsVideo-generation and editing model that accepts images (character/product/style), short motion clips (inputs up to three seconds), and audio cues; produces videos with improved speech narration, clearer lip-sync, and ability to distinguish multiple speakers; handles complex continuous camera movements with fewer unwanted jump cuts.
BENCHMARKS

Not established from the available sources.

AVAILABILITY
Product and API integrationsRolled out through the Gemini API and across Google products, including Google AI Studio, the Google Cloud Console, Flow, Google Vids, the Gemini app for Google AI Ultra subscribers, and Google Ads.
Google Vids free generation quotaIn Google Vids, anyone with a Google account or Google Workspace can generate up to three 15-second videos per month at no cost.

RELEASE TIMELINE

Published, source-backed release events only.

4 SOURCES · IMPORTANCE 8.0

Google releases Gemini Omni 1.2 Flash — cheaper, faster 15‑second video generation

Google is rolling out Gemini Omni 1.2 Flash across the Gemini API and Gemini for Business, lowering the price 30% from Omni 1.1 to $0.07/second for 720p and adding native 3–15 second video generation (up to 15s), multi‑turn conversational editing, and improved reference-following for stronger visual and audio consistency.

→

VERIFIABLE FACTS

Every value stays attached to a source and date.

CONTEXT WINDOW · Maximum generated clip durationDEVELOPER CLAIM

Generates and edits native videos up to 15 seconds long; duration can be specified in one-second increments from 3 to 15 seconds.

CAPABILITIES · Conversational (multi-turn) editingDEVELOPER CLAIM

Supports multi-turn conversational editing (step-by-step edits such as changing background, lighting, or aspect ratio without regenerating the entire clip) across the full 15-second length.

CAPABILITIES · Reference following and visual consistencyDEVELOPER CLAIM

Enhanced reference following and stronger consistency: faces, garments, packaging typography, and brand colors remain consistent across camera angles with less visual drift or morphing versus the predecessor.

MODALITIES · Input modalities and output improvementsDEVELOPER CLAIM

Video-generation and editing model that accepts images (character/product/style), short motion clips (inputs up to three seconds), and audio cues; produces videos with improved speech narration, clearer lip-sync, and ability to distinguish multiple speakers; handles complex continuous camera movements with fewer unwanted jump cuts.

AVAILABILITY · Product and API integrationsDEVELOPER CLAIM

Rolled out through the Gemini API and across Google products, including Google AI Studio, the Google Cloud Console, Flow, Google Vids, the Gemini app for Google AI Ultra subscribers, and Google Ads.

WHAT CHANGED

Stored passport versions, without reconstructed history.

Passport created8 facts