45-second Short from three MiniMax H3 Max clips at 1080p: $9.10
Three 15-second 9:16 MiniMax H3 Max jobs at 1080p cost $9.00, plus $0.10 to join them in Timeline: $9.10 for a 45-second YouTube Short.

A 45-second vertical Short on Sume's MiniMax H3 Max at 1080p is three 15-second jobs at $0.20 per second, $9.00 in total, plus $0.10 for one Timeline render minute: $9.10. Dropping to 768p halves the clip cost to $4.50 ($4.60 with the join).
YouTube says Shorts are vertical videos up to 3 minutes long with a 1080p maximum upload resolution (YouTube Help, read 2026-10-09), so 1080p is the top of what a Short can use. H3 Max is the one MiniMax model on Sume that reaches it.
Price table for 45 seconds
MiniMax H3 Max accepts 5 to 15 seconds per job and lists 9:16 in its aspect ratios, so 45 seconds is exactly three full-length clips. Docs note that 1080p on H3 Max is a latent refinement from native 768p.
| Resolution | Rate per second | 3 clips (45 s) | With Timeline join |
|---|---|---|---|
| 768p | $0.10 | $4.50 | $4.60 |
| 1080p | $0.20 | $9.00 | $9.10 |
Submit the three clips
Send three requests to the video API with the same style line in each prompt. Each returns a job id and a polling URL; poll until the status is completed, then import the finished files so Timeline can read them from media.sume.com (imports go through POST /v1/media-imports).
curl -X POST https://api.sume.com/v1/videos \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"minimax-h3-max","prompt":"Scene 1 of 3: ...",
"aspect_ratio":"9:16","resolution":"1080p","duration":15}'Join them in one 45-second file
Timeline renders at 1080x1920 by default, and it bills $0.10 per output minute rounded up, so 45 seconds is one minute. The audio spine is required: use a voice or music file, or silence while you add sound elsewhere. Starts must increase from 0. The sample adds a 0.25 s fade on each join (a transition can be up to 1 s).
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-45-h3max" \
-d '{"audio":{"mode":"silence","duration_seconds":45},
"video":[
{"source_url":"https://media.sume.com/artifacts/artf_demo/clip1.mp4","start":0,"duration":15},
{"source_url":"https://media.sume.com/artifacts/artf_demo/clip2.mp4","start":15,"duration":15,"transition":{"type":"fade","duration":0.25}},
{"source_url":"https://media.sume.com/artifacts/artf_demo/clip3.mp4","start":30,"duration":15,"transition":{"type":"fade","duration":0.25}}],
"output":{"width":1080,"height":1920}}'Limits worth knowing
- MiniMax H3 Max durations are 5 to 15 seconds, so you cannot ask for 45 in one job.
- The cheaper minimax-h3 stops at 768p in the catalog; only H3 Max lists 1080p.
- Prices are per second at the tool's rate on 2026-10-09; read GET /v1/videos/models for the live pricing_skus before a large batch.
- Three separate generations will not share exact character details unless you pass the same reference images to each.
Sources
Related posts
More in Pricing
- A $47.50 wallet: how many images each Sume image model makes
With $47.50 on Sume you get 1,919 GPT Image 2.5 low images or 237 Nano Banana 2.1 4K images. Full table of 10 image rows with the division shown.
- $47 of 15-second clips: how many fit on Seedance, Wan and MiniMax H3
A $47 balance buys 41 fifteen-second MiniMax H3 clips at 768p, 25 on Wan 3.0 at 720p, 8 on Seedance 2.0 and 5 on Seedance 2.5. Arithmetic and leftovers.
- 47 meeting recordings of 52 minutes: transcription cost on Sume
Transcribing 47 recordings of 52 minutes costs $24.44 on Sume STT at $0.01 per audio minute, as 282 requests of up to 10 minutes each.
- 47,000-character chapter: TTS in three requests, $2.2325 on Sume
Sume text to speech costs $0.0475 per 1,000 characters and one request caps at 20,000 characters ($0.95). A 47,000-character chapter needs three requests.
Written by Sume