AI video model
Produce premium, cinematic clips with Google Veo 3.1 Pro — native synced audio, resolution up to 4K, and reference-image guidance, all in one CreateVision AI workspace.
Compare Veo 3.1 Pro with other video models — same workspace, one click to switch.
A glimpse of what people are creating with AI video models on CreateVision AI.
Veo 3.1 Pro is Google's top-tier Veo tier: filmic motion and lighting, native synced audio generated in the same pass, resolution up to 4K, and reference-image guidance for first-frame or first-and-last-frame control.
Veo 3.1 Pro is tuned for the most demanding shots — believable lighting, depth, and motion that read as professionally produced. When a clip needs to look like a finished commercial rather than a tech demo, this is the tier to reach for.
Audio is generated inside the same pass with believable sync, so dialogue, ambience, and effects arrive attached to the picture. There is no separate sound step to line up in post — the clip comes out complete.
Choose 720p, 1080p, or 4K, and a 4-, 6-, or 8-second length, with audio toggled per generation. Each combination prices transparently before you commit, so premium quality stays a deliberate decision.
Provide a reference image to drive a first-frame or first-and-last-frame generation, anchoring the look or framing of the shot. Pair it with a prompt to direct camera and action from a fixed starting point.
One account, the full image and video generation workflow.
Start free with daily credits. Upgrade for premium models, faster generation, and 4K output.
Perfect for getting started
Billed annually · $240/year
Billed annually · $300/year
Veo 3.1 Pro is the premium tier of Google's Veo 3.1 video model, focused on cinematic quality with native synced audio and resolution up to 4K.
Pro targets the highest visual quality and is priced accordingly; Fast is the faster, lower-cost tier. Both support audio and resolutions up to 4K — Pro is the choice when polish matters most.
Yes — native audio is generated in the same pass with believable sync, and can be toggled on or off per generation.
720p, 1080p, and 4K, at 4, 6, or 8 seconds. Higher resolution, longer duration, and audio all affect the price, which is shown before you generate.
Yes — supply an image to drive a first-frame or first-and-last-frame generation and anchor the shot's look or framing.
It is priced per second by resolution and audio. As a premium tier it costs more than Fast, and the exact total is shown up front with automatic refunds on failed runs.
