
On March 31, 2026, Google released Veo 3.1 Lite, the lowest-cost model in the Veo 3.1 family. Google says it costs "less than 50% of the cost of Veo 3.1 Fast, but with the same speed", and aimed it at developers building "high-volume video applications". It makes the same kind of video as the other Veo 3.1 tiers — a short clip from a prompt or a photo, with sound generated alongside the picture — and gives up a few premium features to get the price down.
This article covers what launched, how Lite differs from Veo 3.1 and Veo 3.1 Fast, and when the cheaper tier is the right one.
Veo 3.1 Lite at a glance
- Released: March 31, 2026, in the Gemini API and Google AI Studio (paid tier).
- Inputs: text to video and image to video.
- Output in Google's API: 720p or 1080p, 16:9 or 9:16, 4, 6 or 8 seconds (1080p requires 8 seconds), 24 fps.
- Audio: generated with every clip, as on the other Veo 3.1 tiers.
- Price and speed: under half the cost of Veo 3.1 Fast at the same generation speed, according to Google. Google also announced a Veo 3.1 Fast price cut for April 7, 2026.
- Not included in Google's version: 4K, video extension and reference images.
Where Lite sits in the Veo 3.1 family
Google now offers Veo 3.1 in three tiers. The original Veo 3 is marked deprecated in the Gemini API.
| Tier | Best for | Notes from Google's documentation |
|---|---|---|
| Veo 3.1 | The final, most detailed take | 720p, 1080p, 4K; reference images; extension |
| Veo 3.1 Fast | Everyday work at a lower price | Same feature set as Veo 3.1, tuned for speed and business use |
| Veo 3.1 Lite | Drafts and high-volume clips | 720p and 1080p; no reference images or extension; lowest cost |
All three generate sound and accept text or an image as the starting point. Google's API also accepts a last frame on Lite, so you can set both where a shot starts and where it ends.
What Veo 3.1 Lite can do
Text to video with sound
Describe a scene and Lite builds it from scratch, including the camera, the action and the soundtrack. The clip below is a Veo 3.1 Lite text-to-video example with a small everyday story in one shot.
Because the audio is generated with the picture, a clip arrives with ambience and effects that match the scene. You can steer it in the prompt by naming the sounds you want and putting spoken lines in quotes.
Image to video
Upload a photo and it becomes the first frame; the prompt then only needs to describe the motion, the camera and the sound. This is the mode to use for product photos, portraits or a still you have already approved.
Landscape or vertical
Lite supports 16:9 and 9:16, so the same prompt can produce a widescreen clip or a vertical one for YouTube Shorts, Instagram Reels and TikTok.
Veo 3.1 Lite vs Veo 3.1
| Veo 3.1 Lite | Veo 3.1 | |
|---|---|---|
| Text to video, image to video | Yes | Yes |
| Sound generated with the video | Yes | Yes |
| First and last frames | Yes | Yes |
| Resolution in Google's API | 720p, 1080p | 720p, 1080p, 4K |
| Reference images (up to 3) | No | Yes |
| Extension (+7 s per step) | No | Yes |
| Relative cost | Lowest of the three tiers | Highest |
Google has not published a quality comparison between Lite and the full model, so the practical way to decide is by job. Lite is the tier for trying prompts, producing many variations and making clips where volume matters more than the last bit of detail. The full Veo 3.1 tier is for the take you will publish: a hero shot, an ad, a scene where dialogue has to sound right.
Who Veo 3.1 Lite is for
- Social video creators who post often and need vertical clips with sound, and who want to try several versions of an idea before keeping one.
- Developers and product teams building video features into apps, where per-clip cost decides what is feasible. This is the audience Google named at launch.
- Anyone drafting prompts for a more expensive tier. Working out the action, the camera move and the sound on Lite costs a fraction of doing it on Veo 3.1.
Launch context
Lite arrived a week after OpenAI announced, on March 24, 2026, that it would discontinue its Sora app and API. If you are moving off Sora, see Sora 2 shutdown: Veo 3.1 as an alternative.
How to try Veo 3.1 Lite
Veo 3.1 Lite is the default video model on Veo Video. Each generation is an 8-second clip with sound, from a prompt or a photo, with an optional end frame. On Veo Video, Lite also renders at 4K, so you can pick 720p, 1080p or 4K, in 16:9 or 9:16.
A Lite clip costs 30 credits at 720p, 35 at 1080p and 150 at 4K. New accounts get 30 free credits, which covers one 720p Lite clip, enough to test a prompt with sound before you buy credits. When a prompt works, you can re-run it on Lite at a higher resolution, or on Veo 3.1 for the most detailed take. Each run is a new take, so expect a close match to your draft rather than an identical clip.
