Veo 3.1 🧠 Model Paid

What it is

Veo is Google DeepMind's video generation family. The current version, Veo 3.1, turns a text prompt or reference images into short clips with sound generated in the same pass: dialogue, sound effects and ambience. A cheaper Lite tier reached the API in March 2026. Gemini Omni Flash, a separate conversational video model launched in May 2026, now sits next to Veo in the Gemini app and Flow.

Key features

• Native audio: speech, sound effects and ambience come out with the picture
• 1080p and 4K output, in 16:9 landscape or native 9:16 portrait
• 8-second base clips. Scene extension builds longer sequences
• Several reference images to keep a character or product consistent
• Every clip carries an invisible SynthID watermark

Where you can use it

Gemini app, Google Flow, Google Vids, AI Studio and the Gemini API. Outside Google, Veo 3.1 is a documented option in Adobe Firefly (as a partner model in Firefly Boards), Higgsfield, Krea, Freepik, Leonardo.Ai, Luma's app and invideo AI. OpenArt lists Veo 3, and Canva's 'Create a Video Clip' runs on Veo 3 (paid plans).

Pricing and rights

Gemini API prices per generated second, audio included (September 2026): Veo 3.1 Standard $0.40 at 720p/1080p and $0.60 at 4K. Fast is $0.10-0.30. Lite is $0.05 at 720p and $0.08 at 1080p. In the Gemini app and Flow it comes with Google AI subscriptions (prices not verified here). Partner apps charge their own credits.

Who it is for

Filmmakers, ad makers and social teams who want realistic short shots with sound, and developers who want a per-second API.

Verdict

Veo 3.1 gives strong realism and some of the best built-in audio, and it is available in more apps than most video models. Base clips are short. Google's own docs say short lines of dialogue can still sound off. Google's newer effort is going into Gemini Omni, so expect the line to change.