Veo 3.1

What is Veo 3.1?

Veo 3.1 is Google DeepMind's video model that generates sound with the picture: dialogue written into the prompt, effects and ambience. It turns text or an image into a 4, 6 or 8 second clip at 720p, 1080p or 4K, in landscape or portrait. Up to three reference images keep a subject's look, a first and last frame fix how a shot opens and closes, and extension grows a clip 7 seconds at a time.

It is still on sale, in a Standard and a cheaper Fast version, but it is no longer Google's first choice: the Gemini API now points developers to Gemini Omni Flash, and Google is replacing Veo with Omni in the Gemini app.

Is Veo 3.1 still available?

Yes, for developers and in Google Flow, but Google no longer treats it as its main video model and is replacing it in the Gemini app.

Gemini API

Still a preview model with no shutdown date announced; Google recommends Gemini Omni Flash by default and Veo 3.1 for extension, last-frame control or existing pipelines.

Gemini app

Google is replacing Veo 3.1 with Gemini Omni for making videos.

Google Flow

Offered as Veo 3.1 Quality, Fast and Lite, next to Gemini Omni Flash.

Google Cloud

Generally available as veo-3.1-generate-001 and veo-3.1-fast-generate-001 on the Gemini Enterprise Agent Platform, formerly Vertex AI.

Who is Veo 3.1 best for?

Veo 3.1 suits developers and video teams who need short clips with matching sound and tight control over the shot: a consistent character, a set first and last frame, or one long extended take.

• Consistent characters and products

  Up to three reference images of a person, character or product keep the subject looking the same in the finished clip.

• Planned transitions

  Give it a first and a last frame and it generates the motion between them, which suits scene changes and product reveals.

• Longer single shots

  Extension adds 7 seconds at a time, up to 20 times, for one continuous 720p shot of up to 148 seconds.

• Dialogue and ad clips

  Lines written in quotes come out as spoken dialogue, and users comparing it with Kling often single out its cleaner voices and lip sync.

What's included with Veo 3.1?

Sound generated with the video, up to three reference images, first and last frames, 7-second extensions up to 148 seconds, and 16:9 or 9:16 output up to 4K.

Sound with every clip

Dialogue, sound effects and ambience are generated with the video and are always on.

Reference images

Up to three images of a person, character or product guide an 8-second clip.

First and last frame

Set the opening and closing images and Veo generates the motion between them.

Scene extension

Continue a Veo clip 7 seconds at a time, up to 20 times, at 720p.

Portrait or landscape up to 4K

16:9 or 9:16 at 720p, 1080p or 4K and 24 frames a second; 1080p and 4K clips run 8 seconds.

SynthID watermark

Every clip carries Google's invisible SynthID watermark, which Google's verification tool can detect.

How does Veo 3.1 work?

1. Send a prompt

   Call veo-3.1-generate-preview or the Fast model with a prompt of up to 1,024 tokens, plus any start, end or reference images.

2. Wait for the job

   Each request runs as a long job that you poll until it finishes; Google puts it at 11 seconds to 6 minutes at busy times.

3. Download within 2 days

   Google deletes videos from its servers after 2 days, so save a copy; extending a clip resets that timer.

How much does Veo 3.1 cost?

Veo 3.1 costs $0.40 per second of video at 720p or 1080p and $0.60 at 4K on the Gemini API's paid tier, or from $0.10 a second on Veo 3.1 Fast; there is no free API tier.

All prices are for video with sound, in US dollars, and you pay only when a video generates. An 8-second 1080p clip costs $3.20 on Veo 3.1 Standard and $0.96 on Veo 3.1 Fast. The Gemini API has no free tier for Veo, and paid-tier prompts and videos are not used to improve Google's products. In Google Flow, everyone gets 50 free credits a day; a Veo 3.1 Fast clip uses 20 credits and a Quality clip 100. Full pricing on ai.google.dev. We checked these prices on 28 Sep 2026.

How do readers rate Veo 3.1?

No one has rated Veo 3.1 yet. Be the first.

Veo 3.1 pros and cons

Veo 3.1's sound and shot controls are strong, but motion glitches, the $0.40 Standard price and Google's move to Omni Flash count against it.

What are the best Veo 3.1 alternatives?

Gemini Omni 1.1 Flash for editing and Google's current default, Kling 3.0 for 15-second multi-shot scenes, and Wan 3.0 for 30-second clips at a lower price.

Gemini Omni 1.1 FlashFree

Choose it when you want to edit clips with follow-up prompts or need 10-second clips; it is now Google's default video model and costs about $0.10 a second at 720p.

Kling 3.0Freemium

Choose it when you want multi-shot scenes of up to 15 seconds in one generation; its API costs $0.126 a second at 720p with sound, about a third of Veo 3.1 Standard.

Wan 3.0Free

Choose it when you want one clip of up to 30 seconds in a single pass; Alibaba Cloud lists it at $0.10 a second at 720p, a quarter of Veo 3.1 Standard, though it stops at 1080p.

Questions about Veo 3.1