Google Veo
Google DeepMind's video model with audio, now the specialist beside Gemini Omni
Overview
Google Veo is Google DeepMind's video generation model. Veo 3.1 makes 8-second clips with generated audio at up to 4K, in landscape or vertical format, with reference images, frame control and scene extension. It is sold per second through the Gemini API and Google Cloud, and Google is replacing it with Gemini Omni in the Gemini app.
Pricing
Pricing shown for reference only. These figures reflect RECATOOLS research as of 14 Oct 2026 and may be out of date or incomplete. This is not financial or purchasing advice — always confirm the current price on the provider’s official website before making any decision.
- 8-second clips, 16:9 or 9:16
- Up to 3 reference images; first and last frames
- Extension by 7 seconds, up to 148 seconds in total
- Faster generation
- 720p, 1080p or 4K
- Fastest Veo 3.1 model
- No 4K output
- Veo 3.1, Fast and Lite, with or without audio
- Veo 3.1 with audio $0.40/second, 4K $0.60
- 1,000 Google Flow credits a month
- Limited trial of Veo 3.1 Lite in the Gemini app
- Gemini Omni Flash in Gemini and Flow
- 10,000 or 25,000 Google Flow credits a month
- Video generation with Veo 3.1
- Higher Gemini Omni Flash limits
Use cases
What you can produce with Google Veo
- 8-second video clips with generated dialogue, sound effects and ambient audio
- Vertical 9:16 clips for Shorts, Reels and similar formats
- 4K video output from Veo 3.1 or Veo 3.1 Fast
- Clips guided by up to three reference images of a person, character or product
- Transitions generated between a specified first and last frame
- Scenes extended seven seconds at a time to as long as 148 seconds
ASEAN Perspective
Google Veo in Southeast Asia
Available across the region through the Gemini app and YouTube; enterprise access via Vertex AI with Google Cloud regional options. Free-credit availability varies by country.
Veo 3.1 remains a capable model for short clips with sound: 8 seconds at up to 4K, vertical output, reference images, first- and last-frame control and extensions up to 148 seconds through the API. Per-second API pricing is published and runs from $0.05 for Lite to $0.60 for full-quality 4K.
The caveat is direction of travel. Google now steers consumers and developers towards Gemini Omni, which replaces Veo in the Gemini app and is the API's recommended default. Choose Veo for extension and frame control or an existing pipeline; for conversational editing, start with Omni.
What we found
Veo is Google DeepMind's video generation model, first shown at Google I/O on 14 May 2024 as a 1080p text-to-video model. Veo 3 added audio generated alongside the picture, and Veo 3.1, still the current version on DeepMind's model page, produces 8-second clips at 720p, 1080p or 4K in landscape or vertical 9:16, with up to three reference images, first- and last-frame control and scene extension. Through the Gemini API a Veo clip can be extended seven seconds at a time, up to 20 times, to a combined 148 seconds.
The larger change is where Veo now sits. In May 2026 Google introduced Gemini Omni, a multimodal model that generates and edits video through conversation, and Google's Gemini pages say Omni will replace Veo in the Gemini app. The subscription pages describe Flow access in terms of Gemini Omni Flash, and the Gemini API documentation tells developers to use Omni Flash by default and keep Veo 3.1 for scene extension, last-frame control or existing pipelines. Veo has not been discontinued, but it is becoming the specialist option.
Developers pay per second, and Google lists no free tier. On the Gemini API, Veo 3.1 costs $0.40 a second at 720p or 1080p and $0.60 at 4K, Veo 3.1 Fast from $0.10 and Veo 3.1 Lite from $0.05, with no 4K on Lite. Google Cloud's Agent Platform, formerly Vertex AI, charges the same for video with audio and less without it, down to $0.03 a second for silent Lite clips at 720p.
Consumers reach it through Google AI plans. A visitor from Singapore sees SGD 6.98 a month for Plus, 28.99 for Pro and 139.99 or 289.98 for the two Ultra levels, with 200 to 25,000 Flow credits. Google says English prompts are fully supported and other languages have not been evaluated, so they may work with varying results. Videos made in the Gemini app carry Google's SynthID watermark.
Compiled by RECATOOLS from public sources: vendor documentation and pricing, code repositories and published reporting.
Notable facts
- Generates synchronised audio — dialogue, music and sound effects — together with the video
- Veo 3.1 added true 4K and native 9:16 vertical video for Shorts/TikTok
- Powers Google's Flow filmmaking tool and appears in YouTube Shorts/Create
- Often tops AI-video quality leaderboards alongside Kling and Runway
Frequently asked questions
About this listing
This entry was compiled from publicly available data including Google Veo's official website, press releases, documentation, and reputable third-party publications. RECATOOLS is not affiliated with Google Veo unless explicitly stated.
Third-party AI tools update their pricing, features, availability, and policies frequently. Information here may be outdated by the time you read this — we make reasonable efforts to keep listings current, but cannot guarantee absolute accuracy.
For the latest details, please refer to Google Veo directly →
Spotted something out of date? Suggest an update →
Related reading
Alternatives to Google Veo
More in Video & Audio
