> ## Documentation Index
> Fetch the complete documentation index at: https://docs.zerogen.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Veo 3.1

> Google's video model, with sound, image references and extending a video.

Veo 3.1, from Google, makes high-quality video with sound. Choose a tier under
**Tier**:

| Tier | Best for | Resolutions |
| - | - | - |
| **Standard** | The highest quality | 720p, 1080p, 4K |
| **Fast** | A balance of quality and cost. The default. | 720p, 1080p, 4K |
| **Lite** | The lowest cost | 720p, 1080p |

## What you can give it

* **A prompt** on its own.
* **Frames**: a start frame, or first and last frames.
* **References** (Standard and Fast): 1 to 3 images. Videos made from
  references are 8 seconds long.
* **Extend** (Standard and Fast): one video of up to 30 seconds. Veo adds 7
  seconds at 720p.

## Output settings

| Setting | Options |
| - | - |
| Aspect ratio | 16:9 or 9:16. With frames or extending, **Auto** follows the input. |
| Duration | 4, 6 or 8 seconds. |
| Audio | On or off. Sound costs more. |
| Quantity | 1 to 4 videos. |

The Fast tier can't make 4K from references.

## Cost

Veo is priced per second of video, by tier and resolution, with more for
sound. A 4-second 720p video with sound on the Fast tier costs about \$0.78.
Prices are as of October 28, 2026.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.