Google DeepMind·Gemini Omni

Gemini Omni Flash Preview

The original Gemini-native video generation and conversational editing model, with a model card first published in May 2026 and an API preview in June.

SunsettingVideo generationWeights not released

The old preview API is scheduled to close on 2026-09-30; Gemini Omni 1.1 Flash is its replacement.

MODEL NUMBER348

First public date: 2026-05
Organization: Google DeepMind
Family: Gemini Omni

Specifications

Only published specifications are shown.

Input modalities: Text · Image · Audio · Video↗
Output modalities: Video · Audio
Open weights: No
Status: Sunsetting↗
Retirement date: 2026-09-30

Overview

Release dates

May 2026 — Gemini Omni Flash Preview was announced. ↗

Architecture & capabilities

Release history

2026-05Announcement

Gemini Omni Flash Preview was announced.

View source

2026-06-30Preview

Gemini Omni Flash Preview entered the video-generation API.

View source

Related models

Select a card to view the related model.

SuccessorGemini Omni 1.1 FlashView details →

Sources

Gemini Omni Flash model cardGoogle DeepMind · Published 2026-08-27

Official · Verified 02

Gemini API release notesGoogle

Official · Verified

Suggest a correction

Copy this template, add the field, proposed value, and primary source, and share it with the archive maintainer.

Model ID: gemini-omni-flash-preview
Page: https://llmlineage.com/en/models/gemini-omni-flash-preview
Field:
Proposed value:
Primary source URL:
Reason: