VEO 3 and VEO 3 Fast – New pricing, new configuration, better resolution

I'm launching three major VEO updates today. Vertical format output (9:16 aspect ratio), 1080p HD output, and New, low price. It also has the VEO 3 and VEO 3 stable at high speed and ready for production use scaled with the Gemini API.

Less VEO

Today, we use VEO 3 and VEO 3 to generate high quality videos, making high quality videos with overall price reductions more affordable.

VEO 3: Now $0.40/sec;It was $0.75/sec

VEO 3 Speed: Now $0.15/sec;It was $0.40/sec

Vertical video and 1080p support

With VEO 3 and VEO 3 fast, you can now set the aspect ratio to 9:16 to generate vertical video formats that are perfect for mobile-first and social use cases. Simply set the “Aspectratio” parameter to “9:16” and you're ready.

It also allows you to generate VEO 3 and VEO 3 high speed videos in 1080p HD. This allows you to create even higher quality by setting the “Resolution” parameter to “1080p”.

To show you how you can build a new experience, check out the Mediasim Demo app in Google AI Studio. It demonstrates how to integrate the TLDRAW SDK into an interactive canvas and combine Gemini's multimodal understanding, generation and image editing with VEO 3 video and audio generation capabilities to create multimodal media simulations.

Start building in VEO 3 in minutes

This release makes it more affordable for building applications that support a high-quality video generation. I'm looking forward to seeing what developers will create with VEO 3 and VEO 3!

Here is a basic Python example for creating videos (use the latest) google-genai Version):

import time
from google import genai
from google.genai import types

client = genai.Client()

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="720p",
    ),
)

# Waiting for the video(s) to be generated
while not operation.done:
    time.sleep(20)
    operation = client.operations.get(operation)
    print(operation)

generated_video = operation.response.generated_videos[0]
client.files.download(file=generated_video.video)
generated_video.video.save("golden_retriever.mp4")

Python

prompt

_1:_{Shot is a lonely rock climber, climbing a snowy mountain at sunrise. Capture her as she navigates the section. The camera is only a few feet away. She smirks at the camera in professional admiration. Wiping her brows with her gloved hands, she looks at the lens firsthand and says in an impressive, enthusiastic tone, “The Veo 3 is 50% cheaper and high quality, so before continuing to climb.”}

_2:_{Generate high-resolution videos shot in ultra-slow motion with a macro lens. This video captures a drop of magic ink falling into crystal clear water. Rather than simply clouding the water, the ink blooms in miniatures, living, etheric dioramas filled with animals and flowers, before they gently fade away.}

_3:_{A cinematic time-lapse video that germinates a single seed, grows into lush plants and blooms in vibrant flowers, all set against subtly changing backgrounds suggesting the passing of the season. Focusing on the complex details of plant development and the interaction of light and shadows}

Source link