11 three-second shots on Omni Flash: $1.24 at 360p to $12.38 at 4K

Eleven 3-second shots are 33 seconds. On Gemini Omni Flash 1.1 that costs $1.2375 at 360p, $4.125 at 720p, $6.1875 at 1080p and $12.375 at 4K. Three seconds is the model's minimum, so no shot can be shorter.

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 shot and per tier

Native audio is always on for Omni, and the docs say Sume bills the provider list × 1.25 per output second as a function of resolution. So the audio is not an extra line.

A two-pass plan

Render all eleven at 360p ($1.2375), pick the four that work, and re-render those at 4K: 4 × 3 s × $0.375 = $4.50. The whole plan is $5.7375, against $12.375 for eleven at 4K at once.

Wan 3.0 would take 2 s shots, so the same count of 2-second shots at 1080p is 22 s, $5.50; the shots would be shorter, so the comparison is by count and length, not only by price.

Scaling this plan up or down

As a yardstick, the plan above is built on Gemini Omni Flash 1.1 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 (10 s) holds $1.25 at submit. The shortest one (3 s) holds $0.375.

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 (10 s): $1.25

Check the model's fields first

Before a run, ask GET /v1/videos/models for the model and compare three fields with your plan: supported_durations (every clip length must be listed), supported_resolutions (the tier must be listed, since MiniMax H3 has 768p and no 1080p, and Omni has 360p and 4K) and supported_aspect_ratios. A request outside those lists fails at validation, so the failure costs nothing, but a plan built on a wrong assumption costs a rewrite.

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. Omni accepts aspect_ratio 16:9 or 9:16 only.