model release

Google launches Gemini Omni Flash, multimodal video generation model available to AI Plus subscribers

TL;DR

Google has released Gemini Omni Flash, the first model in its new Gemini Omni family designed to generate video content from text, images, video, and audio inputs. The model is available now to AI Plus subscribers, with free access coming to YouTube Shorts and YouTube Create later this week.

2 min read
0

Gemini Omni Flash at a glance

Context window131K tokens
Input$1.5/1M tokens
Output$9/1M tokens

Google launches Gemini Omni Flash, multimodal video generation model available to AI Plus subscribers

Google has released Gemini Omni Flash, the first model in its new Gemini Omni family designed to generate video content from multiple input types. The model is available now to subscribers of AI Plus and higher tiers, with free access coming to YouTube Shorts and YouTube Create later this week.

Model capabilities

Gemini Omni accepts text, images, video, and audio inputs (currently limited to speech samples) to create unified video outputs. According to Google, the model maintains a "cohesive, grounded world" with realistic physics and sound effects. Users can refine generated videos in subsequent turns after initial generation.

Google demonstrated the model generating a video of a rolling marble with what the company claims are believable physics for ball movement and convincing sound effects for bounces and bell rings. Another demo showed a claymation-style explainer video about protein folding.

Availability and pricing

Gemini Omni Flash is available immediately to AI Plus subscribers and higher tiers. Pricing for AI Plus subscription was not disclosed. Free access through YouTube Shorts and YouTube Create will launch later this week.

Google teased a higher-tier "Omni Pro" model with details coming soon.

Safety measures

All videos created by Gemini Omni include SynthID watermarking to identify AI-generated content. The model allows users to create personalized avatars of themselves for video generation. Audio and speech editing capabilities are not yet enabled — Google stated it will add this "until [it] can bring this capability to users responsibly."

Context

The release builds on Google's previous work with the Genie model for interactive video-game-style experiences and its Veo video generation models. Unlike Genie, which remains limited to AI Ultra subscribers, Google is positioning the Omni series for broader access.

What this means

Google is entering direct competition with OpenAI's Sora in consumer video generation, choosing broader distribution through free YouTube integration rather than a paid-only model. The phased rollout of audio editing capabilities and mandatory watermarking suggests the company is prioritizing safety controls over feature completeness at launch. The tiered model structure (Flash and Pro) mirrors Google's strategy across its Gemini lineup, though concrete capability differences and Pro pricing remain undisclosed.

Related Articles

model release

Google releases Genie 4 to AI Ultra subscribers with real-time prompt editing and native audio

Google is rolling out Genie 4, which it calls its most realistic and interactive world model yet, to eligible Google AI Ultra subscribers in Project Genie. The update adds real-time native audio, mid-session text prompting, a world-building agent and a community gallery. Genie 3 also gains sessions of up to 3 minutes.

model release

Google releases Gemini 4 Neon at $3/$15 per 1M tokens with a 1M-token context window

Google released Gemini 4 Neon, available today through the API at $3 per million input tokens and $15 per million output tokens. It is the fourth new Gemini 4 model in four weeks, with a context window of about one million tokens.

model release

Tencent releases Hy4 flash: 220B MoE, 12B active parameters, 1M-token context

Tencent has released Hy4 flash, a multimodal Mixture-of-Experts model with 220B total parameters, 12B active per token, and a 1,048,576-token context window. Tencent calls it its most cost-effective Hy model to date and claims a per-task cost of 1/20 that of Hy4 on its internal WorkIndex benchmark.

model release

Tencent releases Hy4 Flash Base: 220B-parameter MoE, 12B active, 1M-token context

Tencent has published Hy4 Flash Base on Hugging Face: a 220B-parameter mixture-of-experts model with 12B active parameters per token, text and image input, and a 1M-token context. Tencent calls it its most cost-effective Hy model to date.

Comments

Loading...