The $0.125 music bed is 25% of a 3-second clip and 0.6% of a 1080p one
A flat $0.125 bed is 25% of a 3 s Omni clip and 0.6% of a 15 s Seedance 2.5 1080p clip. The share for seven clip types, with the arithmetic.
The Music 1.0 price is a flat $0.125 per generation, so its share of a clip's cost depends only on how expensive the footage is. Against a 3-second Gemini Omni Flash 1.1 clip at 720p ($0.375) the bed is 25% of the total ($0.125 / $0.50). Against a 15-second Seedance 2.5 clip at 1080p ($21.3233) it is 0.6%.
That spread changes which question matters. For a short, cheap clip, the bed is a quarter of the bill and re-rolling it twice doubles the audio cost. For an expensive clip, the bed is a rounding error and the real cost is re-rolling the footage. The numbers below use the Sume prices read from the public catalog on 2026-10-08.
The table
Per-second prices (Sume list, default options): Omni 720p $0.125, Wan 3.0 480p $0.0625, Wan 3.0 720p $0.125, MiniMax H3 Max 768p $0.10, Seedance 2.5 720p $0.5778, Seedance 2.5 1080p $1.42155. Clip cost is rate x seconds, then the bed is added.
| Clip | Clip cost | Clip + bed | Bed share |
|---|---|---|---|
| Omni 720p, 3 s | $0.375 | $0.50 | 25% |
| Wan 3.0 480p, 6 s | $0.375 | $0.50 | 25% |
| Omni 720p, 10 s | $1.25 | $1.375 | 9.1% |
| H3 Max 768p, 15 s | $1.50 | $1.625 | 7.7% |
| Wan 3.0 720p, 15 s | $1.875 | $2.00 | 6.25% |
| Seedance 2.5 720p, 8 s | $4.6224 | $4.7474 | 2.6% |
| Seedance 2.5 1080p, 15 s | $21.3233 | $21.4483 | 0.6% |
Reading the table
Three practical points follow.
- Omni 720p and H3 Max already carry native audio, so on those rows the bed is optional. The Sume docs say Omni's native audio is always on, and H3 Max renders native stereo audio. Adding a bed there is a choice, not a need.
- At 480p a 6-second Wan 3.0 clip ($0.375) costs as much as a 3-second Omni 720p clip, and the bed share is the same 25%. The share tracks footage dollars, not seconds.
- Timeline assembly is separate. A render is $0.10 per started output minute, so a clip under 60 seconds adds $0.10 whatever its length. For the 3-second Omni row the full chain is $0.375 + $0.125 + $0.10 = $0.60, and the bed plus render is 37.5% of it.
What to do with the share
If the bed is 25% of your unit, test the sound once on a 480p or short proxy and re-roll the footage at final resolution only after the bed is chosen. If the bed is under 3%, spend the effort on the clip. A Music 1.0 re-take is $0.125 whatever the clip, as the Music 1.0 page states: the price does not change with prompt length or image conditioning.
One caution on scope. These are list prices for default options and one clip, with no retries, captions or upscales. They show how the bed compares to footage, not what a finished ad costs.
Sources
Related posts
More in Pricing
- Music for 20 video ads, three takes each: 60 generations, $7.50
Sume Music is a fixed $0.125 per accepted generation, whatever the prompt length. Three takes for each of 20 ads is 60 generations and $7.50. Arithmetic inside.
- Music Router: 24 takes cost $3.00, every model charges $0.125
Sume's Music Router charges the fixed Music price per audio generation whichever model it picks. Twenty-four takes cost 24 x $0.125 = $3.00.
- Music Router at 12.5 cents a song vs ElevenLabs at 15 cents a minute
Sume's Music Router charges a fixed $0.125 per generation. ElevenLabs lists Music at $0.15 a minute, and Gemini lists Lyria 3.5 at $0.08 a song. The sums.
- Nano Banana 2.1 for 400 product images: $30 at 0.5K up to $80 at 4K
Nano Banana 2.1 replaced Nano Banana 2 on Sume this week. 400 images cost $30 at 0.5K, $40 at 1K, $60 at 2K and $80 at 4K. Arithmetic and a mixed plan.
Written by Sume