Veo 3.1
13 modes on this page
Veo 3.1 is Google DeepMind's flagship video model, generating short clips with synchronized native audio from a text prompt.
Input
FormMode
Prompt*
Image URL*
Aspect Ratio
Resolution
Duration
Result
PreviewMotion preview, not Veo 3.1 output
$0.3 per second·~90s
What Veo 3.1 is for
Veo 3.1 from Google turns a written prompt into a short video clip. Runtime is about 90 seconds and compute is $0.3 per second. Modes on this page: Image to Video (Fast), Image to Video, Image to Video (Lite), Text to Video (Fast), Text to Video, Text to Video (Lite), Reference to Video, First/Last Frame to Video, First/Last Frame to Video (Fast), First/Last Frame to Video (Lite), Extend Video (Fast), Extend Video, and Reference to Video (Fast). It is a clip generator, not a full training-video editor.
Veo 3.1 is billed in Knowlify credits at the compute cost ($0.3 per second). A typical run is about 90 seconds. Published rate: For every second of video you generate you will be charged $0.10 without audio or $0.15 with audio for 720p or 1080p. At 4k, you will be charged $0.30 per second without audio, or $0.35 with. For example, a 5 second video at 1080p with audio on will cost $0.75.
Pick Veo 3.1 for text to video at $0.3 per second and ~90s. Compare it with Gemini 25 Flash, Gemini 3, Gemini 3.1 Flash Image Preview on the related cards below if you need a different look, speed, or input type.
How to use Veo 3.1
- 1. Upload the still Veo 3.1 should start from, then write the change or motion in Input.
- 2. Run it. The prompt and file hand off to the Knowlify studio, where Veo 3.1 generates.
- 3. Stay in the studio if you want that frame or clip inside a longer narrated video.
What you need
- A prompt that names the subject, camera move, and lighting.
- A source still (PNG or JPG) for the model to start from.
- Aspect Ratio (16:9, 9:16).
- Resolution (720p, 1080p, 4k).
- Optional toggles on this model, such as audio or quality flags.
Example prompt
a crimson sports car drifting a wet mountain switchback at dusk, aerial tracking shot, rain, headlights, no text
Frequently asked questions
How do I run Veo 3.1?
Run Veo 3.1 on Knowlify at /generate/veo-3-1. This page has 13 modes in one dropdown. Write the prompt on this page and it opens in the studio, where Veo 3.1 generates a short clip. The same studio also turns documents into full narrated videos.
Where can I use Veo 3.1 online?
On Knowlify (Google's model, knowlify.com/generate/veo-3-1). You do not need a separate playground. Veo 3.1 runs in the studio next to document-to-video.
Can I make a longer video with Veo 3.1?
Veo 3.1 itself produces a short clip. On Knowlify you can take that output, or skip it and upload a document, and generate a full narrated video with a script you can edit.
What do I need to run Veo 3.1?
A prompt and a source still. Veo 3.1 will not invent the starting frame for you on this mode.
How long does Veo 3.1 take?
Plan on about 90 seconds for a typical run, then whatever queue time the studio has. Video models sit at the high end of that range.
Does Veo 3.1 have more than one mode?
Yes. This page has 13 modes: Image to Video (Fast), Image to Video, Image to Video (Lite), Text to Video (Fast), Text to Video, Text to Video (Lite), Reference to Video, First/Last Frame to Video, First/Last Frame to Video (Fast), First/Last Frame to Video (Lite), Extend Video (Fast), Extend Video, and Reference to Video (Fast). Switch them in the Mode dropdown instead of opening a new URL.
How much does Veo 3.1 cost per video?
Veo 3.1 is $0.20 per second at 720p or 1080p without audio, and $0.40 per second with audio. A 5-second 1080p clip with audio costs about $2.00 on Knowlify credits.
What is the difference between Veo 3.1 and Veo 3.1 Fast?
Fast is roughly half the price, at $0.10 per second without audio and $0.15 with, and generates more quickly. Standard Veo 3.1 resolves motion and detail better. For drafts and iteration, Fast is usually the better economics.
Can Veo 3.1 generate audio?
Yes, Veo 3.1 generates synchronized native audio including dialogue and ambient sound. Audio doubles the per-second cost, so it is off by default here.
How long can a Veo 3.1 video be?
This generator supports 4 to 8 seconds per clip. Longer sequences are produced by generating multiple clips and extending them, which the Veo 3.1 extend endpoint supports.