Veo 3.1
Veo 3.1 is Google DeepMind's flagship video model, released on 15 October 2025 as the successor to Veo 3 with richer native audio, up to three reference images, first-and-last-frame transitions and scene extension. It is the model inside the Gemini app's Ultra plan, Flow and YouTube, and on the API it is the most expensive per second on this site: $0.40 with audio at 720p or 1080p, $0.60 at 4K.
Anvisha Pai, Co-founder & CEO, Voyager
Google DeepMind · released
›What we asked for
A self-portrait of Veo 3.1, Google's video model: a nature-documentary shot of a hummingbird hovering at a red flower in a misty forest, wings audible, dew on the petals, slow motion, narrator-free natural sound.
fal-ai/veo3.1
aspect_ratio: 16:9, resolution: 720p, duration: 6s, generate_audio: true
returned 1280 by 720 pixels
At a glance
- Price
- $0.40 a second with audio at 720p or 1080p, $0.60 at 4K, $0.20 silent. Our six-second clips cost $2.40 each.
- Length
- 4, 6 or 8 seconds only; our five-second fixture rounds to six.
- Audio
- Native dialogue, effects and ambience, on by default.
- 4K
- The only tier of the three that renders 4K.
- References
- Up to three reference images and first-and-last-frame transitions on the API.
Other Veo models: Veo 3.1 Fast, Veo 3.1 Lite. Compare all 3.
Anvisha's take
Veo 3.1 is the most polished set on the roster and the dearest. The title card is perfectly typeset, the glass spill throws real droplets, the market is dense and legible, and the woman speaking to camera reaches for the lens like a selfie. At $2.40 for six seconds it costs more than four Veo 3.1 Fast clips, and side by side the Fast set is close enough that most people should look there first. Pay for the full model on hero shots and 4K.
Veo 3.1 real output: the same 9 clips every model gets
Every video model on this site gets the same 9 clips, so you can compare like with like. These are the clips Veo 3.1 returned, one try each, nothing re-rolled or retouched. Each tile shows one frame of the clip until you press play. Generated on . The 9 clips took 67 to 108 seconds each and cost $21.60 in total.
A clean product shot that holds its shape through a full slow rotation.
›What we asked for
A matte black ceramic pour-over coffee dripper rotating slowly on a white turntable, soft studio light, seamless white background, product video, no text.
fal-ai/veo3.1
aspect_ratio: 16:9, resolution: 720p, duration: 6s, generate_audio: true
returned 1280 by 720 pixels
A face, lip sync and a spoken line, where the model makes audio.
›What we asked for
A woman in her 40s with short grey hair stands in a bright kitchen, looks at the camera and says 'Good morning, the coffee is ready', natural window light, handheld feel, she smiles at the end.
fal-ai/veo3.1
aspect_ratio: 16:9, resolution: 720p, duration: 6s, generate_audio: true
returned 1280 by 720 pixels
Set text that stays spelled correctly while it moves.
›What we asked for
A title card reading 'MODA SUMMER SESSIONS' animates in over slow-motion footage of a festival crowd at dusk, then a smaller line 'Friday 12 June' fades in beneath it. Bold condensed type, tangerine on navy.
fal-ai/veo3.1
aspect_ratio: 16:9, resolution: 720p, duration: 6s, generate_audio: true
returned 1280 by 720 pixels
A steady drone push-in with stable geometry.
›What we asked for
Drone shot pushing slowly forward over a coastal town at sunrise, terracotta roofs, fishing boats in the harbour, long shadows, cinematic and steady.
fal-ai/veo3.1
aspect_ratio: 16:9, resolution: 720p, duration: 6s, generate_audio: true
returned 1280 by 720 pixels
A spill in slow motion: does water behave like water.
›What we asked for
A glass of water tips over on a wooden table and spills in slow motion, water and three ice cubes sliding across the wood, macro lens, morning light.
fal-ai/veo3.1
aspect_ratio: 16:9, resolution: 720p, duration: 6s, generate_audio: true
returned 1280 by 720 pixels
Hands, a kettle and a steady pour without extra fingers or teleporting objects.
›What we asked for
Close-up of hands pouring hot water from a gooseneck kettle in slow circles into a pour-over coffee dripper, steam rising, shallow depth of field, warm cafe light.
fal-ai/veo3.1
aspect_ratio: 16:9, resolution: 720p, duration: 6s, generate_audio: true
returned 1280 by 720 pixels
Many people and objects moving at once without merging.
›What we asked for
A crowded Saturday farmers market seen from slightly above, shoppers with tote bags, a dog on a leash, a busker with a guitar, bunting swaying, late morning light, gentle camera drift.
fal-ai/veo3.1
aspect_ratio: 16:9, resolution: 720p, duration: 6s, generate_audio: true
returned 1280 by 720 pixels
A named style held across every frame rather than drifting to photoreal.
›What we asked for
A lighthouse on a rocky cliff in a storm, in the style of a Japanese ukiyo-e woodblock print, waves crashing in flat colour with visible wood grain, animated like moving paper cutouts.
fal-ai/veo3.1
aspect_ratio: 16:9, resolution: 720p, duration: 6s, generate_audio: true
returned 1280 by 720 pixels
Bring a still product photo to life without changing the product.
›What we asked for
The coffee dripper slowly fills as coffee drips through it, steam rising, the camera drifting gently around it, the dripper itself unchanged. (starting from The Nano Banana Pro product shot from the image fixture set.)
fal-ai/veo3.1/image-to-video
aspect_ratio: 16:9, resolution: 720p, duration: 6s, generate_audio: true
returned 1280 by 720 pixels
How the cost under each picture was worked out: fal's Veo 3.1 rate of $0.40 per second at 720p with audio on (fal model page, read 2026-09-09) for the 6 seconds requested; fal does not return the charge.
Compare Veo 3.1
Veo 3.1 pricing
| Where | Unit | Price | Source |
|---|---|---|---|
| Gemini API | Second with audio, 720p or 1080p $0.60 at 4K. No free tier. | $0.40 | Gemini API pricing, read |
| fal | Second with audio, 720p or 1080p $0.20 silent; 4K $0.40 silent, $0.60 with audio. fal's example: five seconds at 1080p with audio is $2.00. | $0.40 | fal model page, read |
| fal | Six-second 720p clip with audio | $2.40 | fal model page, read |
Is Veo 3.1 free?
There is no free tier for Veo on the Gemini API. In the Gemini app, video generation is a paid-plan feature: Google AI Pro accounts get up to three Veo 3.1 Fast clips a day and Google AI Ultra up to five with the full Veo 3.1, with occasional free weekends for everyone.
- •Gemini API: Google's pricing page lists the free tier as not available for every Veo 3.1 model.
- •Gemini app, Google AI Pro: up to three videos a day on Veo 3.1 Fast.
- •Gemini app, Google AI Ultra: up to five videos a day on Veo 3.1.
- •Every clip carries a SynthID watermark.
iTechGuides on Gemini app video limits, 13 August 2026, read
Where to use Veo 3.1
- Gemini app · Paid plans; a few clips a day.
- Google Flow · Google's filmmaking tool built on Veo.
- Gemini API and Vertex AI · Pay per second, with and without audio.
- fal · Per-second pricing by resolution and audio; text, image and first-last-frame endpoints.
- Voyager · Runs inside Voyager, the agent for creative work. Private preview by waitlist.
Voyager
Run Veo 3.1 inside Voyager
Voyager is an agent for creative work that runs every model in this reference, Veo 3.1 included. Brief it, and it picks the model, makes the thing and hands back something you can edit. Create an account to get started.
What we noticed running Veo 3.1
- •Framed the speaker as a selfie with her arm extended to the camera, which the prompt did not ask for. Veo likes to invent a reason for the camera. See the person speaking clip.
- •The best spill on the roster: the glass rolls, ice skids, and the water spreads with visible droplets. See the physics clip.
- •Self-portrait: The self-portrait prompt produced a hummingbird at a red flower in the rain, gorgeous and nothing to do with Veo.
- •Cannot make a five-second clip; the fixture rounds to six seconds, so every clip here is 6.0 seconds and priced at six.
Veo 3.1 limits and API parameters
| Limit | Value |
|---|---|
| Length | 4, 6 or 8 seconds. fal API reference, read |
| Resolution | 720p, 1080p or 4K in 16:9 or 9:16. fal API reference, read |
| References | Up to three reference images on the Gemini API. |
›Every setting, for developers
fal (fal-ai/veo3.1)
fal API reference, read
| Parameter | Type | Values | Default |
|---|---|---|---|
| prompt | string | Any text Required. | |
| duration | enum | 4s, 6s, 8s | 8s |
| resolution | enum | 720p, 1080p, 4k | 720p |
| aspect_ratio | enum | 16:9, 9:16 | 16:9 |
| generate_audio | boolean | true, false | true |
| negative_prompt | string | Any text | |
| seed | integer | Any integer | |
| auto_fix | boolean | true, false Rewrites a prompt the safety filter would refuse. | true |
| safety_tolerance | enum | 1 to 6, 1 strictest | 4 |
| image_url | URL | Starting frame, 720p or higher Image-to-video endpoint. |
What Veo 3.1 will not make
Google's Generative AI Prohibited Use Policy applies: no sexual content involving minors, non-consensual intimate imagery, violent extremism, self-harm, hate, harassment or deceptive depictions of real people, and no adult mode. Every clip carries an invisible SynthID watermark, and fal exposes a safety_tolerance dial from 1 to 6 that operates inside the same policy.
Alternatives to Veo 3.1
Frequently asked questions
What is Veo 3.1?
Veo 3.1 is Google DeepMind's flagship video model, released on 15 October 2025, with native audio, reference images, first-and-last-frame transitions and 4K output, available in the Gemini app, Flow, the Gemini API and on fal.
How much does Veo 3.1 cost?
$0.40 a second with audio at 720p or 1080p and $0.60 at 4K on both the Gemini API and fal, read on 9 September 2026. A six-second 720p clip with audio is $2.40.
Is Veo 3.1 free?
Not on the API. In the Gemini app it is a paid-plan feature: a few Veo 3.1 Fast clips a day on Google AI Pro and a few full Veo 3.1 clips on Ultra.
Is Kling AI better than Veo 3?
On price, Kling 3.0 is less than half the cost per second. On output, both pages here run the same nine clips, so look rather than take anyone's word.
How this page is made
Prices, limits and settings are read from the linked vendor and host pages on the dates shown. Every picture was generated by us through fal with the request shown under it, and the original files are kept unedited. A generation that failed is shown as a failure. Model and vendor names are used to identify the products; no vendor imagery appears on this page.
