Veo 3.1 clips are 4, 6 or 8 s: when 10 s needs Omni instead
Veo 3.1 clips are 4, 6 or 8 seconds. For a 10 second shot, Gemini Omni Flash 1.1 on Sume outputs 3 to 10 seconds. A duration table and what stays unavailable.

Veo 3.1 in the Gemini API supports only 4, 6 or 8 second clips, so a single 10 second shot is not available from it. Gemini Omni Flash outputs 3 to 10 seconds at 360p, 720p, 1080p and 4K, and Sume exposes it as gemini-omni-flash-1.1. Sume does not list a Veo id, so Veo itself is not callable there.
Sources are Google's Veo 3.1 docs, the Gemini Omni Flash model page and the Gemini API pricing page, read on 2026-10-03.
Duration side by side
Veo's docs add that 8 seconds is required for extension, reference images and for 1080p and 4k. Omni's page has no such coupling: durations from 3 to 10 seconds are listed at every resolution.
| Item | Veo 3.1 | Gemini Omni Flash |
|---|---|---|
| Durations | 4, 6 or 8 seconds | 3 to 10 seconds |
| Resolutions | 720p default, 1080p and 4k | 360p, 720p, 1080p, 4K |
| 1080p / 4K length | 8 seconds only | Listed at 3 to 10 seconds |
| Aspect ratios | 16:9 and 9:16 | 16:9 and 9:16 |
| Reference images | Up to 3 (8 seconds required) | Image and video references |
Price per second as published
Google's pricing page lists Veo 3.1 Standard at $0.40 per second at 720p and 1080p and Fast at $0.10 at 720p. Omni is listed at about $0.10 per second at 720p. A 10 second Omni clip at the list price is 10 x 0.10 = $1.00; on Sume at list x 1.25 that is $1.25. Veo Fast at 8 seconds and 720p is 8 x 0.10 = $0.80 at Google's price, and only on Google's own API.
Pick by what the shot needs
If your edit calls for a 10 second beat, Omni removes the stitching. If you need Veo's 4 second or 6 second lengths or its extension chain, you would call Google directly; that is outside Sume's catalog. A 10 second Omni request is below.
curl -X POST https://api.sume.com/v1/video-router/generate \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: omni-10s-001" \
-d '{
"model": "gemini-omni-flash-1.1",
"prompt": "In a single continuous shot, a hot air balloon rises over a misty valley at sunrise.",
"resolution": "720p",
"duration": 10,
"aspect_ratio": "16:9",
"mode": "async"
}'Where to read more
The Video Router docs list capabilities and the live catalog. Check Google's pages again before you budget, since prices and limits change.
Sources
Related posts
More in Comparisons
- Veo 3.1 tiers vs Seedance 2.5: price per second of video
Google lists Veo 3.1 at $0.40 (Standard), $0.10-$0.12 (Fast) and $0.05-$0.08 (Lite) per second; Seedance 2.5 on fal is about $0.46 at 720p. Sume x 1.25: $0.58.
- Veo 3.1 vs Gemini Omni Flash 1.1: what Sume can call
Google lists Veo 3.1 at 1080p and 4K with native audio. On Sume, Gemini Omni Flash 1.1 is the callable Google id: 3-10 s, 360p-4K, audio always on.
- Voice agent latency claims: 100 ms, 150 ms, 90 ms and Sume TTS jobs
ElevenLabs and Cartesia quote 90 to 150 ms for live voice. What those figures measure, and why Sume TTS jobs are for produced audio rather than live calls.
- Voice agent platforms at 10,000 minutes: eight price lists compared
Telnyx about $596, Deepgram and AssemblyAI $750, Bland $1,400 to $1,499, Retell $700 to $3,100: eight published rates at 10,000 minutes.
Written by Sume