Veo

0:43 Veo is Google DeepMind's AI video model, and its newest version, Veo 3.1 (announced Oct 15, 2025), turns text or images into clips of 4, 6 or 8 seconds with generated sound, at 720p, 1080p or 4K. As of Nov 6, 2026 you can use it in three places: Google Cloud, where Veo 3.1 costs $0.40 a second with audio at 1080p (Fast $0.10 to $0.30, Lite $0.05 to $0.08); Google Flow, where Veo 3.1 Lite costs 10 credits a clip out of 50 free daily credits; and the Gemini app. The Gemini API's Veo 3.1 previews were shut down on Oct 22, 2026.

Google's own newer model, Gemini Omni (May 19, 2026), now outranks Veo: Gemini Omni 1.2 Flash is first on Arena's text-to-video leaderboard while Veo 3.1 is 14th (Arena, read Nov 6, 2026), and Flow is retiring Veo 3.1 Fast and Quality on Dec 5, 2026. Pick Veo 3.1 today for a stable, generally available API with 4K output and published per-second prices; pick Gemini Omni for the best measured quality and editing; look at Kling for single shots up to 30 seconds or Wan if you need open weights. Best AI Video Generator compares them all.

Quick facts

Veo price

Google Cloud bills Veo per second of video. Sound costs extra, so each model has a price with audio and a cheaper one without.

Source: Google Cloud generative AI pricing, read Nov 6, 2026. An 8-second 1080p Veo 3.1 clip with sound is therefore $3.20, and the same clip on Veo 3.1 Lite is $0.64.

In Google Flow, a Veo 3.1 Lite clip of 4, 6 or 8 seconds at 720p costs 10 credits, or 5 for Google AI Ultra subscribers, and Ultra 20x subscribers can make them for 0 credits in a slower Lower Priority mode (Google Flow Help). Flow gives everyone 50 credits a day; Google AI Pro adds 1,000 a month and Ultra 10,000 or 25,000.

Where can you use Veo?

Google Cloud. The generally available models are veo-3.1-generate-001 and veo-3.1-fast-generate-001, released Nov 17, 2025, with Google promising support until at least May 4, 2027; veo-3.1-lite-generate-001 is in preview (Google Cloud). This is the place for developers now.

Gemini API and AI Studio. The preview models veo-3.1-generate-preview, veo-3.1-fast-generate-preview and veo-3.1-lite-generate-preview were shut down on Oct 22, 2026, and Veo 2 on Jun 30, 2026. Google points developers to Gemini Omni Flash or to the Google Cloud models (Gemini API docs).

Google Flow. Flow, Google's filmmaking tool, offers Veo 3.1 Lite alongside Gemini Omni Flash 1.2. Veo 3.1 Fast and Veo 3.1 Quality stay until Dec 5, 2026, and Flow's Veo Extend was retired on Nov 5, 2026 (Google Flow Help).

1:59 Gemini, Google Photos and Google Vids. Google DeepMind's Veo page still links to the Gemini app and Google Vids (Google DeepMind). Google AI Pro and Ultra add Veo 3 image-to-video in Google Photos, in the US only (Google One).

Features

3:07 Sound in the same pass. Since Veo 3, Veo generates dialogue, sound effects and ambient noise with the video. Google notes that short spoken lines can still come out garbled (Google DeepMind).

Ingredients and frames. Veo 3.1 can follow up to three reference images of a character, object or scene, or move between a first and a last frame you supply (Gemini API docs).

Extend. A Veo clip can be extended by 7 seconds at a time, up to 141 seconds in all, at 720p (Gemini API docs).

Editing. Google lists inserting and removing objects, outpainting, camera and motion controls and style references among Veo's tools (Google DeepMind).

History

• May 20, 2025: Veo 3 arrives with native audio, first for Google AI Ultra subscribers in the new Google Flow (Google).
• Oct 15, 2025: Veo 3.1 adds richer audio, reference images and frame control, in Flow, the Gemini API, Vertex AI and the Gemini app (Google).
• Nov 17, 2025: Veo 3.1 and Veo 3.1 Fast become generally available on Google Cloud.
• Apr 2, 2026: Veo 3.1 Lite, the low-cost model, released in preview (Google Cloud).
• May 19, 2026: Google introduces Gemini Omni Flash, a newer video model, in Flow (Google).
• Oct 22, 2026: Veo 3.1 previews shut down in the Gemini API.
• Dec 5, 2026: Veo 3.1 Fast and Quality leave Flow (announced).

Veo vs the alternatives

Gemini Omni is Google's newer model. Omni 1.2 Flash ranks 1st on Arena text-to-video at 1541 against Veo 3.1's 1363, makes clips of up to 15 seconds and can edit existing video in conversation; through the API it is billed by tokens, about $0.07 a second at 720p, with no free API tier. Veo 3.1 keeps the advantage of a generally available model with a published support date.

Kling 4.0 makes up to 30 seconds in one take, about four times Veo's 8 seconds (Bernama).

Seedance 2.0 and 2.5 rank 6th and 7th on Arena, well above Veo 3.1, and are sold inside Runway, Luma and Pika as well as by ByteDance.

Wan is the pick for running video generation on your own computer; Veo has no open weights.

Sora, OpenAI's former rival, closed in 2026.

Frequently asked questions

How much does Veo 3.1 cost? On Google Cloud, Veo 3.1 costs $0.40 a second with audio at 720p or 1080p and $0.60 at 4K; Veo 3.1 Fast costs $0.10 to $0.30 and Veo 3.1 Lite $0.05 to $0.08, as of Nov 6, 2026.

Can I use Veo for free? Yes, a little: Google Flow gives everyone 50 credits a day, and a Veo 3.1 Lite clip costs 10 of them, so five short 720p clips a day, as of Nov 6, 2026.

Is Veo 3.1 still in the Gemini API? No. The Veo 3.1 preview models in the Gemini API shut down on Oct 22, 2026; Veo 3.1 remains on Google Cloud as veo-3.1-generate-001.

Is there a Veo 4? Google had announced no Veo 4 as of Nov 6, 2026. Its newest video model is Gemini Omni, introduced on May 19, 2026.

How long can a Veo video be? A single Veo 3.1 clip is 4, 6 or 8 seconds; extending adds 7 seconds at a time, up to 141 seconds.

Does Veo make sound? Yes. Veo 3 and Veo 3.1 generate speech, sound effects and ambient audio with the video.

Sources

• Veo, Google DeepMind, read Nov 6, 2026
• Veo 3.1 models, Google Cloud, read Nov 6, 2026
• Generative AI pricing, Google Cloud, read Nov 6, 2026
• Generate videos with Veo 3.1 in Gemini API and Pricing, Google AI Studio, read Nov 6, 2026
• Manage your Google Flow credits and Google Flow models and supported features, Google Flow Help, read Nov 6, 2026
• Google AI plans, Google One, read Nov 6, 2026
• Flow, AI filmmaking with Veo 3 (launch post), Google, May 20, 2025
• Veo 3.1 and new Flow capabilities (announcement), Google, Oct 15, 2025
• Google Flow updates at I/O 2026, Google, May 19, 2026
• Text-to-video leaderboard, Arena, read Nov 6, 2026
• Kling AI Officially Launches Next-Generation Kling 4.0, Bernama, Oct 19, 2026
• Google Veo 3 Tutorial: Make Cinematic AI Videos with Just a Prompt, Kevin Stratvert, Jul 3, 2025 (video)