YouTube Shorts' free Veo 3 Fast clip is 480p: what Sume models render
YouTube's 2025 announcement put Veo 3 Fast in Shorts at 480p with sound. Sume's router lists 720p and 1080p models; check the ceilings before you pick.

YouTube's in-app Veo 3 Fast generates clips for Shorts at 480p with sound, free, according to YouTube's own September 2025 blog post. YouTube's Shorts help says you can upload Shorts at a maximum resolution of 1080p (YouTube Help), so a 480p clip is low resolution for a full-screen phone. If you need sharper footage, Sume's video router lists models at 720p and 1080p, and one at 4K, but each has its own duration and ratio limits. The list below is what the docs say, not a quality ranking.
What YouTube said
Unpacking the magic of our new creative tools, read 2026-10-04, announces Veo 3 Fast in Shorts: generation from a text prompt, now with sound, at 480p with lower latency, free, rolling out in the United States, United Kingdom, Canada, Australia and New Zealand. The post also says YouTube applies SynthID watermarks and content labels across these features. It is a 2025 announcement; the current help page, Create content for Shorts using AI-generated features, describes the standalone clip tool as producing videos up to 10 seconds without naming a resolution, so confirm what the app gives you today.
What the Sume docs list
The Video Router page gives per-model ranges. Prices are not repeated here because they change; read them from GET /v1/catalog.
| Model or path | Duration | Resolution | Aspect ratios named |
|---|---|---|---|
| Video Router Auto (sume/auto) defaults | 8 s default, 3 to 10 s | 720p default | 16:9 or 9:16 |
| seedance-2.5 | 4 to 30 s | 480p, 720p, 1080p | Set with aspect_ratio |
| wan-3.0 | 2 to 30 s | See catalog | See catalog |
| gemini-omni-flash-1.1 | 3 to 10 s | 360p, 720p, 1080p, 4K | 16:9 or 9:16 |
| minimax-h3-max | 5 to 15 s | 480p, 768p, 1080p (1080p refined from 768p) | See catalog |
Picking for a Short
For a hook clip of a few seconds, the Auto defaults are enough to test a concept. For a final render that will be stretched to a phone screen, choose a model with a 1080p option and set aspect_ratio to 9:16. Gemini Omni Flash 1.1 always carries synced audio; for other models, plan audio separately and join it in Timeline 1.0, which renders 1080x1920 by default and charges $0.10 per ceil output minute.
One honest limit: resolution is not the same as quality. A 1080p tag tells you the pixel grid, not whether faces or text hold up. Generate a short test, pull a still with video frames, and look at it before you queue a batch. The jobs and results page covers polling for each clip.
Sources
- YouTube Blog: Unpacking the magic of our new creative tools (read 2026-10-04)
- YouTube Help: Create content for Shorts using AI-generated features (read 2026-10-04)
- YouTube Help: YouTube Shorts requirements (read 2026-10-04)
- Sume docs: Video Router
- Sume docs: Video generation
- Sume docs: Timeline 1.0
- Sume docs: Jobs and results
Related posts
More in Models
- YouTube Speech to Song vs Sume Music Router: prompt in, audio out
YouTube's Speech to Song turns a Short's speech into a song with Lyria 2. Sume's Music Router takes a text prompt (and an optional image), with no audio input.
- Is Z-Image Turbo on Sume? Not listed: the cheapest rows instead
Sume's image catalog on 2026-10-04 has no Z-Image row. Check with one request and see the cheapest listed models: Soul $0.005, Grok and Qwen $0.025.
- 1,000 SKU catalog of 6 s Grok Imagine loops: $75 plus image prep
Grok Imagine Video on Sume bills $0.0125 a second: 1,000 six-second loops are $75.00, with no audio or aspect_ratio. Add 9:16 prep photos and submit in waves.
- 21:9 AI video with sound for $3: MiniMax H3 Max 1080p vs Seedance 2.5
A 15-second 21:9 clip with native audio costs $3.00 on MiniMax H3 Max at 1080p and $21.43 on Seedance 2.5 at 1080p in Sume's pricing tables. Limits compared.
Written by Sume