Video model · Google
Veo 3.1
Google's flagship Veo video model
Also known as Veo 3, Veo
What is Veo 3.1?
Veo 3.1 is Google's flagship AI video model. It generates high-quality clips from text or an image, supports reference images for consistency, and can interpolate between a first and last frame.
Capabilities
- Generate video from a text prompt
- Animate a still image into video
- Keep characters and products consistent with reference images
- Fill in the motion between a first and last frame
Veo 3.1 on Melius
Melius runs Veo 3.1 alongside every other major image, video, audio, and text model, so you can generate with it, compare it against the field, and let the Mel agent route to it automatically — all on one infinite canvas. You only pay for what you generate.
Frequently asked questions
What is Veo 3.1?
Veo 3.1 is Google's flagship AI video model. It generates high-quality clips from text or an image, supports reference images for consistency, and can interpolate between a first and last frame.
Is Veo 3 available on Melius?
Yes. Veo 3 is Veo 3.1 on Melius. Add it to any canvas node and generate, compare it against every other model, or let the Mel agent route to it automatically. You only pay for what you generate.
How do I use Veo 3.1 on Melius?
Melius is a node-based canvas: add a node, pick Veo 3.1 from the model picker, and connect it to whatever should feed it or follow it. You can also just describe what you want and let the Mel agent wire it up. You only pay for what you generate.