Cheapest 1080p AI video per second on Sume, ranked, 21 s example

Ranked by price per second at 1080p on Sume: Gemini Omni Flash 1.1 $0.1875, MiniMax H3 Max $0.20, Wan 3.0 $0.25, Seedance 2.0 $0.8505, Seedance 2.5 $1.42155. MiniMax H3 has no 1080p tier. A 21-second clip costs between $3.94 on Omni and $29.85 on Seedance 2.5, although not every model takes 21 s in one job.

Prices on this page are Sume list prices as of 2026-10-08: the provider list price times 1.25, computed from Sume's pricing package and billed per output second, linear in duration inside each model's valid range. The model ids, ranges and input types come from the Video generation docs and the Video Router docs; the per-second numbers can be cross-checked in the public catalog.

A 21-second example

Omni stops at 10 s and Seedance 2.0 and the MiniMax models stop at 15 s, so for the first, second and fourth rows the 21 s is two jobs (on Omni, 21 s needs three jobs such as 7 + 7 + 7; on the others two jobs such as 10 + 11). The linear price makes the total the same however it is split, but the number of joins changes.

Reading the ranking

The cheapest per second is not always the cheapest per delivered minute: Omni needs the most joins, and its 1080p rate also includes native audio. Wan 3.0 is 33 percent dearer per second than Omni and takes 21 s in one job. Seedance 2.5 is 7.58 times the price of Omni at 1080p.

Pick by what the clip needs: audio-on by default (Omni), single continuous shot (Wan 3.0, Seedance 2.5), reference video and audio inputs (Seedance 2.x, Wan 3.0, MiniMax H3 and H3 Max).

Scaling this plan up or down

As a yardstick, the plan above is built on Gemini Omni Flash 1.1 at 1080p, $0.1875 per second. Each extra 5 seconds adds $0.9375, a further $10 of budget buys 53 more whole seconds, and the largest single job the model accepts (10 s) holds $1.875 at submit. The shortest one (3 s) holds $0.5625.

Those three numbers are enough to rescale the plan without a new table. If the plan doubles, double the totals; if a clip is shortened, subtract the seconds multiplied by the rate; and if the tier changes, swap the rate for the one in the tables above.

• Per second: $0.1875
• Per 5 s: $0.9375
• Per 10 s: $1.875
• Per 30 s or the model maximum (10 s): $1.875

Check the model's fields first

Put the price table in your own config and compute the total before you call the API. The price is linear in seconds inside a model's range, so a function of rate and duration is enough, and it lets you refuse a batch that goes over a ceiling. Re-read the catalog when you plan a large run, because list prices are what Sume bills from, and they can change.

Submitting

Submit through POST /v1/videos with model, prompt, duration in whole seconds and resolution; read GET /v1/videos/models first, because supported_durations and supported_resolutions differ per model. Sume reserves the price at submit and usage.cost on the poll response is the billable amount, so the figures here are what leaves the balance.