AI video model · by Google DeepMind
Veo 3.1 video generator
Veo is Google DeepMind's video generation model. MotionLab runs the Veo 3.1 variants that are enabled below, including first-and-last-frame generation where available, so you can direct where a shot starts and where it lands.
Veo 3.1 variants available now
These are the Veo 3.1 variants currently enabled on MotionLab and the settings each one accepts. The table is generated from the live model catalog, so it changes when a variant is added, updated or paused.
| Variant | Modes | Duration | Resolution | Aspect ratios | Audio / end frame |
|---|---|---|---|---|---|
| Google Veo 3.1 Lite | Image to video · Text to video | 4–8s | 720p · 1080p · 4k | 1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 · 2:3 · 21:9 · 9:21 · 5:4 · 4:5 · 2.35:1 · auto | Native audio · End frame |
| Google Veo 3.1 Fast | Image to video · Text to video | 4–8s | 720p · 1080p · 4k | 1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 · 2:3 · 21:9 · 9:21 · 5:4 · 4:5 · 2.35:1 · auto | Native audio · End frame |
| Veo 3.1 | Text to video · Image to video | 4–8s | 720p · 1080p · 4k | 16:9 · 9:16 · 1:1 · 4:3 · 3:4 · 3:2 · 2:3 · 21:9 · 9:21 · 5:4 · 4:5 · 2.35:1 · auto | Native audio · No end frame |
| Veo 3.1 First Last Frame To Video | Image to video | 4–8s | 720p · 1080p · 4k | 1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 · 2:3 · 21:9 · 9:21 · 5:4 · 4:5 · 2.35:1 · auto | Native audio · End frame |
Veo 3.1 price compared with other providers
Prices at matched settings, in US dollars using the Pro credit pack. MotionLab charges the same credits on the website and through the API. Competitor prices link to their source and show the date they were checked.
1 models · 1 options with savings against at least one provider, based on the Pro credit pack. Select a model to see its comparable options.
| Model / settings | MotionLab · Pro | Higgsfield · USD | fal.ai · same settings |
|---|---|---|---|
| $0.3755 | $1.5680 | $1.2000 |
Full methodology: AI API pricing comparison.
What to use Veo 3.1 for
- Shots that need generated sound alongside the picture, when audio is supported for your variant.
- First/last-frame transitions: give a start and an end image and let the model bridge them.
- Quick concept passes with a lighter variant before committing credits to the final take.
- Dialogue-free scene beats, establishing shots and cinematic inserts.
How to use Veo 3.1 on MotionLab
- Sign in and open the video creation page.
- Choose a Veo 3.1 variant in the model picker. Only the variants listed above are shown.
- Write your prompt, add a start image or references if the mode needs them, and pick duration, resolution and aspect ratio.
- Check the credit cost shown for your settings, then generate. Failed jobs are refunded automatically.
- Download the result or keep refining it in your library.
Veo 3.1 prompt tips
- Write the scene like a shot description: subject, action, camera, light, then sound if you want it.
- For first/last-frame jobs, keep both frames in the same lighting and palette so the bridge stays clean.
- Describe sound plainly (rain on glass, distant traffic) rather than with mood words.
- Use the lighter variant to find the shot, then re-run the keeper on the stronger one.
More technique in the MotionLab prompt guide and the camera motion guide.
Compare Veo 3.1 with other models
Veo 3.1 questions
Does Veo 3.1 generate audio on MotionLab?
Where the enabled Veo variant supports native audio, the specs table on this page marks it, and the create page shows the audio option. Variants without audio produce silent video.
What is first/last-frame video?
You provide the opening and closing image and Veo generates the motion between them. It is useful for transitions, reveals and matching cuts.
How much does Veo 3.1 cost on MotionLab?
Veo 3.1 generations spend MotionLab credits from the same wallet used by every model on the site. The credit cost for your exact settings is shown before you generate, and a job that fails is refunded automatically. Credit packs are listed on the pricing page.
Do I need a separate Veo account or API key?
No. MotionLab runs Veo for you: sign in, pick the model in the create page and generate. Your results are saved to your MotionLab library next to work from every other model.