A 10-second 9:16 ad: what each Sume video model costs
Ten seconds of 9:16 video on Sume: H3 768p $0.75, H3 Max 768p $1.00, Wan 720p $1.25, Omni 720p $1.25. All except Wan carry always-on audio.
Every model below accepts 9:16. Prices are Sume billable rates (provider list x 1.25, rounded up to the cent per job), read 2026-10-07.
10-second portrait clip
| Model | Resolution | Audio | 10 s job |
|---|---|---|---|
| MiniMax H3 | 768p | always on | $0.75 |
| MiniMax H3 Max | 768p | always on | $1.00 |
| Wan 3.0 | 720p | toggle (default on) | $1.25 |
| Gemini Omni Flash 1.1 | 720p | always on | $1.25 |
| Gemini Omni Flash 1.1 | 1080p | always on | $1.88 |
For landscape the same table holds with 16:9. The ratios differ: Omni accepts only 16:9 and 9:16, Wan adds 4:3, 3:4 and 1:1 but not 21:9, H3 adds 21:9. Pick the cheapest row that meets your resolution and sound need; H3 wins on price, Wan on references.
Sources
Related posts
More in Comparisons
- Voice agent, TTS API or rendered narration? Pick by output
Decagon Voice 3, MAI-Voice-2.1 Flash, Gemini 3.8 TTS and Sume jobs solve different problems. A decision table for choosing by output, October 2026.
- AI voiceover cost for 100 scripts: Sume vs ElevenLabs v4
100 scripts of 800 characters cost $3.80 on Sume TTS, $6.40 on ElevenLabs v4 at list, or $1.76 under its discount that ends Oct 12.
- Wan 2.7 vs Wan 3.0: clip length and resolution limits by model id
Wan 2.7 tops out at 15 s and starts at 720P; Wan 3.0 reaches 30 s and adds 480P. Alibaba's ids side by side, and which one Sume lists.
- Wan 3.0 or Seedance 2.5: which one for which brief
Pick Wan 3.0 for cheap 2 to 30 s drafts and heavy reference sets; pick Seedance 2.5 for ByteDance's long-take behavior. A decision table from Sume's catalog.
Written by Sume