120-second vertical video at 720p: $9.00 to $69.34 across Sume models

Two minutes of vertical video is $9.00 on MiniMax H3 at 768p, $12.00 on H3 Max at 768p, $15.00 on Wan 3.0 or Gemini Omni Flash 1.1 at 720p, and $69.34 on Seedance 2.5 at 720p, from the Sume price tool on 2026-10-09. A Timeline join of two minutes adds $0.20.

That is two thirds of the 3-minute Shorts limit (YouTube Help, read 2026-10-09), and it is where the clip count starts to differ most between models.

Cost and job count

Wan 3.0 and Seedance 2.5 split 120 s into four 30-second jobs. H3 and H3 Max need eight 15-second jobs, and Omni needs twelve 10-second jobs.

The two-minute boundary

Timeline bills $0.10 per output minute rounded up, so exactly 120 seconds is two minutes. Make it 121 and it is three. For a Short that must also fit the 3-minute ceiling, aim for 120 s or a few seconds under a multiple of 60.

curl -X POST https://api.sume.com/v1/timeline-1.0/render \
  -H "Authorization: Bearer $SUME_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: short-120-001" \
  -d '{"audio":{"mode":"silence","duration_seconds":120},
   "video":[
    {"source_url":"https://media.sume.com/artifacts/artf_demo/clip1.mp4","start":0,"duration":30},
    {"source_url":"https://media.sume.com/artifacts/artf_demo/clip2.mp4","start":30,"duration":30,"transition":{"type":"fade","duration":0.25}},
    {"source_url":"https://media.sume.com/artifacts/artf_demo/clip3.mp4","start":60,"duration":30,"transition":{"type":"fade","duration":0.25}},
    {"source_url":"https://media.sume.com/artifacts/artf_demo/clip4.mp4","start":90,"duration":30,"transition":{"type":"fade","duration":0.25}}],
   "output":{"width":1080,"height":1920}}'

Check before you commit

• Eight or twelve clips from one prompt style drift more than four; a reference image on each job helps.
• Seedance 2.5's 0.5778 is the 720p 9:16 value; its rate depends on resolution and aspect.
• The Timeline plan call is unbilled and returns billable_minutes before you render.
• Native 768p is H3's first-class tier; it is not 720p, so the rows are close, not identical.