Google DeepMind has announced a substantial update to its Veo 3 video generation model, delivering fresh features aimed squarely at creators and developers building the next generation of AI-powered video apps. The newly released enhancements include support for vertical video (9:16 aspect ratio), full 1080p HD output, and significant reductions in usage pricing, making cinematic AI-generated video more accessible and affordable than ever before.

Lower Pricing Makes AI Video Creation More Accessible

In a move set to democratize professional-quality video synthesis, Veo 3 and Veo 3 Fast have new, lower pricing.

• Veo 3: Now $0.40 / second; was $0.75 / second

• Veo 3 Fast: Now $0.15 / second; was $0.40 / second.

New Format Support: Vertical Video and 1080p HD

Creators can now unlock new possibilities with vertical video generation in 9:16 aspect ratio—a format tailor-made for TikTok, YouTube Shorts, Instagram Reels, and other mobile-first platforms. By simply adjusting the ‘aspectRatio’ parameter within the Gemini API, developers can output social-ready, portrait-oriented clips with ease.

Developer Demos Highlight Creative Potential

To showcase what’s possible, Google points to the new MediaSim demo app within Google AI Studio, which integrates Gemini’s image editing, audio generation, and the tldraw SDK for multimodal creativity. This demo app lets developers experiment with combining video, audio, and image generation in new media simulations.

Early Adopters: Invisible Studio, Saga, and Mosaic

Several leading-edge platforms are already leveraging Veo 3’s enhanced capabilities:

• Invisible Studio is building a fully AI-native engine for short-form content creation, relying on Veo 3 for rapid, high-quality video production that accelerates creative workflows and boosts productivity.

• Saga employs Veo 3 and Imagen 4 to streamline the filmmaking process, enabling writers and directors to visualize, iterate, and pitch ideas in record time—from scriptwriting to storyboards to final video.
  

• Mosaic uses Veo 3 for agentic video editing, letting users turn raw footage and prompts into coherent videos (up to 64 seconds) with native audio—an unprecedented leap for long-form video synthesis.

Getting Started: Build with Veo 3 on the Gemini API

Developers can begin generating high-quality videos in just minutes using the latest version of google-genai and the Gemini API. With built-in support for vertical and HD output, Veo 3 enables rapid prototyping and full-scale production of AI-generated videos across creative industries.
All videos continue to include a secure SynthID watermark for provenance.

Example Python Implementation

Here's a snippet showing how to generate a vertical, HD video using Veo 3 Fast:

import time
from google import genai
from google.genai import types

# Initialize client
client = genai.Client()

# Start video generation
operation = client.models.generate_videos(
    model="veo-3.0-fast-generate-001",
    prompt="a close-up shot of a golden retriever playing in a field of sunflowers",
    config=types.GenerateVideosConfig(
        negative_prompt="barking, woofing",
        aspect_ratio="9:16",
        resolution="1080p",
    ),
)

# Wait for the operation to complete
while not operation.done:
    time.sleep(20)
    operation = client.operations.get(operation)
    print(operation)

# Get generated video
generated_video = operation.response.generated_videos

# Download and save the video
client.files.download(file=generated_video.video)
generated_video.video.save("golden_retriever.mp4")

With these updates, Google DeepMind aims to empower an entire ecosystem of video creators—streamlining everything from social storytelling to cinematic, long-form projects—while keeping quality high and costs low.

Footnote Prompts

1. The shot is of a lone rock climber skillfully making her ascent up a snow-capped mountain at sunrise. Capturing her as she navigates a section. The camera is close, just a few feet away. She looks at the camera with a grin of professional admiration. Wiping her brow with a gloved hand, she looks directly into its lens and says with an impressed, enthusiastic tone, "Veo 3 is now like 50% cheaper and higher quality so go build" before turning to continue her climb.

2. Generate a high-resolution video, shot in ultra-slow motion with a macro lens. The video captures a single drop of magical ink falling into crystal clear water. Instead of merely clouding the water, the ink blossoms into a miniature, living, ethereal diorama of nature, filled with animals and flowers, before gently fading out.

3. A cinematic time-lapse video of a single seed sprouting, growing into a lush plant, and then blooming with vibrant flowers, all set against a subtly changing background that hints at the passage of seasons. Focus on the intricate details of the plant's development and the interplay of light and shadow.