Smallest AI video clip you can buy on Sume: shortest length, price
The shortest clips on Sume: Wan 3.0 from 2 s, Gemini Omni Flash from 3 s, Seedance from 4 s. Cheapest test render costs $0.1125, before a $0.0062 fee.

The cheapest video test on Sume is a 3-second Gemini Omni Flash clip at 360p, which sells for $0.1125, or a 2-second Wan 3.0 clip at 480p for $0.125. Seedance starts at 4 seconds: $0.35154 on 2.0 mini and $1.074709 on 2.5. All figures are before the 5.5% fee.
Where the minimums come from
Each model has a duration range in the repo's catalog and docs: Wan 3.0 accepts 2 to 30 seconds, Gemini Omni Flash 1.1 accepts 3 to 10, and Seedance 2.5 accepts 4 to 30 (the 2.0 family 4 to 15). The shortest duration at the lowest resolution gives the smallest price. See the video router docs for current options.
Smallest paid jobs, priced
Video rows use the lowest listed resolution and the model's minimum duration. Non-video rows are the unit prices from the API rate table.
| Job | Sell price | Fee | Hold |
|---|---|---|---|
| Wan 3.0, 2 s at 480p | $0.125 | $0.006875 | $0.131875 |
| Gemini Omni Flash, 3 s at 360p | $0.1125 | $0.006187 | $0.118687 |
| Seedance 2.0 mini, 4 s at 480p | $0.35154 | $0.019334 | $0.370874 |
| Seedance 2.5, 4 s at 480p | $1.074709 | $0.059108 | $1.133817 |
| Music, one track | $0.125 | $0.006875 | $0.131875 |
| Speech-to-text, 1 min | $0.01 | $0.00055 | $0.01055 |
| TTS, 1,000 characters | $0.0475 | $0.002612 | $0.050112 |
Why prototype small
- A 3-second 360p Omni test checks that your prompt and key work for about 11 cents.
- Moving from a 2-second to a 30-second Wan clip multiplies the price by 15 with the resolution unchanged.
- Seedance 2.5 cannot go below 4 seconds, so it is not the model for the cheapest probe.
Balance check
A balance under the hold gets 402 insufficient_credits and nothing is charged. The dollar post shows what $1 covers across all of these.
Sources
Related posts
More in Pricing
- Transcribing 10, 100 and 1,000 hours: AssemblyAI, Scribe, Sume
Speech-to-text list prices per hour, read 2026-10-07 (AssemblyAI, ElevenLabs, Speechmatics, Cartesia, Gladia) beside Sume at $0.60, for 10 to 1,000 hours.
- Splitting a 30-second Wan 3.0 job adds cents from per-job rounding
Wan 3.0 bills linearly per second, but Sume rounds each job up to the cent. A 30 s clip as six 5 s jobs costs $3.78 at 720p instead of $3.75. Full split table.
- Startup $140 and Scale $800 of included usage: seconds of Wan 720p
Startup is $120 with $140 included; Scale is $400 with $800 included. At Wan 3.0 720p ($0.125 a second) that is 1,120 s and 6,400 s of footage.
- Sume price formula: list x 1.25 plus 5.5% fee, worked on six clips
How to predict a Sume bill: provider list price x 1.25 rounded up, then a 5.5% fee floored. Six video clips worked from list cost to hold, in micro-dollars.
Written by Sume