Veo 3.1 Lite and a new Veo upscaling capability on Vertex AI

We are introducing Veo 3.1 Lite, Google’s most cost-effective video model on Vertex AI. 

Alongside this new model, we are also launching a new, standalone Veo upscaling capability on Vertex AI to help you enhance your existing video assets.

Choosing the right Veo model for your workload

When integrating video generation into your applications, matching the model to your specific use case is critical. The Veo 3.1 family now includes three tiers, all of which feature native audio generation capabilities:

• Veo 3.1: This model is designed for state-of-the-art video generation where visual fidelity is the top priority for final production cuts

• Veo 3.1 Fast: This option delivers faster video generation while maintaining high quality, making it ideal for standard production workflows.

• Veo 3.1 Lite: This is our most cost-effective model, empowering businesses to build high-volume video applications and rapidly iterate and scale.

For a pricing breakdown, visit the Vertex AI pricing page.

For a full guide, visit our ultimate prompting guide for Veo 3.1.

Upscale your assets with the new Veo upscaling capability

A highly requested feature from customers is the ability to upscale existing low-resolution videos to higher resolutions. Available in private preview, and coming soon to public preview, the new Veo upscaling capability allows you to enhance your videos up to 1080p and 4K, regardless of whether they were generated by Veo, another AI model, or a traditional camera.

Take a look at this demo to see how Veo brings your idea to life.