A 13-scene, 117-second storyboard at 720p: Wan, Seedance, Omni

Thirteen 9-second scenes (117 seconds) at 720p cost $14.625 on Wan 3.0, $14.625 on Gemini Omni Flash 1.1 and $67.6026 on Seedance 2.5. Each scene is one job, so the storyboard is thirteen jobs.

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.

Per scene and total

Nine seconds is inside every model's valid range (Seedance 2.5 4 to 30 s, Wan 3.0 2 to 30 s, Omni 3 to 10 s), so a scene fits in one job on each of them. MiniMax H3 and H3 Max also take 9 s (5 to 15 s).

Planning the order of jobs

Thirteen jobs of similar length can run in parallel if your plan allows it, and a scene can use the last frame of the previous one as first_frame if the model supports frame images. Check supported_frame_images for the model you pin: the docs list first_frame and last_frame for Seedance 2.0, and MiniMax H3 Max and Omni are documented to take start and end frames.

To keep the spend predictable, price the whole board first with the arithmetic above, then run scene 1 only. If scene 1 passes, the balance needed for the other twelve is 12 × the per-scene figure.

• Wan 3.0 per scene: $1.125
• Re-rolling one scene on Wan 3.0 costs $1.125; on Seedance 2.5 $5.2002.

Scaling this plan up or down

As a yardstick, the plan above is built on Wan 3.0 at 720p, $0.125 per second. Each extra 5 seconds adds $0.625, a further $10 of budget buys 80 more whole seconds, and the largest single job the model accepts (30 s) holds $3.75 at submit. The shortest one (2 s) holds $0.25.

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: $0.125
• Per 5 s: $0.625
• Per 10 s: $1.25
• Per 30 s or the model maximum (30 s): $3.75

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.