A 19-second single shot: which Sume video models take it in one job

Only Wan 3.0 (2 to 30 s) and Seedance 2.5 (4 to 30 s) take a 19-second clip in one job: $4.75 and $27.00945 at 1080p. The other models stop at 15 s (Seedance 2.0, MiniMax H3, H3 Max) or 10 s (Gemini Omni Flash 1.1), so 19 s there is two jobs and a visible join.

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.

One job or two

Where two jobs are needed the split also has to respect each model's minimum. Omni can split 19 as 10 + 9. H3 and H3 Max need two clips of at least 5 s, so 10 + 9 works, or 15 + 4 does not (4 is under 5). Seedance 2.0 can use 15 + 4, as its floor is 4 s.

The join

A split clip needs a match on the cut. With models that take a first frame, you can seed the second job from the last frame of the first, which keeps position and light continuous. Omni documents an end_image_url; Seedance 2.0 lists first_frame and last_frame. The cost of a join is a re-roll risk, not money: the total price is linear in seconds, so the split does not change the sum.

If the whole shot has to be continuous, Wan 3.0 at $4.75 is the cheapest single job in the table.

Scaling this plan up or down

As a yardstick, the plan above is built on Wan 3.0 at 1080p, $0.25 per second. Each extra 5 seconds adds $1.25, a further $10 of budget buys 40 more whole seconds, and the largest single job the model accepts (30 s) holds $7.50 at submit. The shortest one (2 s) holds $0.50.

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: $0.25
• Per 5 s: $1.25
• Per 10 s: $2.50
• Per 30 s or the model maximum (30 s): $7.50

Check the model's fields first

After the first job completes, read usage.cost on the poll response and compare it with the figure in this post. They should agree, because both are the provider list price times 1.25. If your number differs, the usual cause is a different tier or duration than you planned, not a price change; the public catalog at https://api.sume.com/v1/catalog shows the current rates and needs no key.

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.