A finished 30-second vertical ad on Sume: $4.01 to $17.60, itemized
Three 10 s 720p clips, a 450-character voice-over, one music track and a Timeline render cost $4.01 on Wan 3.0 and $17.60 on Seedance 2.5.

The short answer
A finished 30-second 9:16 ad built from three 10-second 720p clips, a 450-character voice-over, one music track and one Timeline render costs about $4.01 on Wan 3.0 and about $17.60 on Seedance 2.5. The video clips are $3.75 to $17.34 of the bill, so the choice of clip model sets the price; voice, music and assembly together add $0.255.
Line by line
Each line uses the Sume billable price on 2026-10-08. The TTS line is 450 characters x $0.0000475 = $0.021375, rounded up to 3 cents. Music is the fixed $0.125 per generation. Timeline 1.0 is $0.10 per rounded-up output minute, and 30 seconds is one minute.
| Clip model | 3 clips | Voice-over | Music | Timeline | Total |
|---|---|---|---|---|---|
| Wan 3.0 | $3.75 | $0.03 | $0.125 | $0.10 | $4.005 (about $4.01) |
| Kling 3 (mute) | $4.20 | $0.03 | $0.125 | $0.10 | $4.455 (about $4.46) |
| Seedance 2.0 Mini | $5.67 | $0.03 | $0.125 | $0.10 | $5.925 (about $5.93) |
| Seedance 2.5 | $17.34 | $0.03 | $0.125 | $0.10 | $17.595 (about $17.60) |
How each number was derived
Wan 3.0 lists $0.10 per second at 720p, so a 10-second clip is $1.00 x 1.25 = $1.25 and three clips are $3.75. Kling 3 without audio lists $0.112 per second, so a clip is $1.12 x 1.25 = $1.40. Seedance rows are token-priced; the grid value for a 10 s 720p 9:16 clip is $1.89 on Seedance 2.0 Mini and $5.78 on Seedance 2.5.
The voice and music lines use the TTS Router and the fixed Music price. Timeline is described on the Timeline 1.0 page.
The same ad at scale
Ten of these ads on Wan 3.0 cost 10 x $4.005 = $40.05. A hundred cost $400.50, with the 12.5-cent music line billed as a fixed amount for each generation. If ten ads share one music track, 10 ads cost 10 x ($3.75 + $0.03 + $0.10) + $0.125 = $38.925. The per-ad price barely moves, because the clips are the bill.
To change the length, scale the clip line. A 60-second ad of six 10-second Wan clips is $7.50 for video, $0.10 for Timeline (60 seconds is one rounded minute), plus voice and music. A 61-second ad adds a second Timeline minute.
What this total leaves out
It assumes every generation is kept. A realistic job has retakes: if you generate each clip twice on Wan 3.0 and keep one, the video line doubles to $7.50 and the ad is about $7.76. It also leaves out any 2K/4K upscale and anything outside Sume, such as caption fonts or stock footage. Clip models differ in what they accept, so read their limits from the catalog before you lock the plan.
The practical use of this table is to find the line to tune. Moving from Seedance 2.5 to Wan 3.0 saves $13.59 on one ad; dropping music saves 12.5 cents.
Sources
Related posts
More in Pricing
- One finished minute: two 30 s Seedance 2.5 shots plus Timeline
A 60-second video from two 30 s Seedance 2.5 shots plus one Timeline render costs $16.24 at 480p, $34.78 at 720p and $85.40 at 1080p.
- One finished minute on Wan 3.0: $3.86 at 480p, $15.10 at 1080p
Two 30 s Wan 3.0 shots plus a Timeline render make a 60-second video for $3.86 at 480p, $7.60 at 720p and $15.10 at 1080p on Sume.
- OpusClip Starter $15 vs Sume trim plus caption at $0.22 a clip
A Sume trim ($0.02) plus caption ($0.20) costs $0.22 per short clip, so $15 buys 68 clips. OpusClip Starter is $15 a month. What the numbers do and do not say.
- Output tokens in a 3 to 10 second Omni clip: 17,376 to 57,920
Gemini Omni Flash bills 5,792 output tokens per 720p second. A 3 s clip is 17,376 tokens and a 10 s clip 57,920. Dollars at Google and on Sume, per length.
Written by Sume