Preview once, render twice: 20 s Standard check $3.68, then Max $11.00

Sume lets you approve one avatar video preview and then choose the tier of the final render at generate-video time. Rendering a 20-second check at Standard ($3.68) before the Max final ($11.00) costs $14.68 in video spend, $3.68 more than going straight to Max.

What the preview docs guarantee

The preview stage generates first-frame stills and does not start the full talking-video render. The docs state that preview stills are tier-independent and that Sume reuses them, so if you approve and then downgrade or upgrade, you do not need a new preview. An empty body keeps the quality chosen at preview create; an optional quality overrides only the final render tier.

Admission, pre-spend, ledger reservation, provider submit and readback all use the effective overridden tier. Structural fields (script, video_inputs, avatar_handle, scene, aspect_ratio) still need a new preview if they change.

Cost of each path for 20 seconds

Rates: Standard $0.184, Plus $0.245, Max $0.55 per second without a product image; $0.194, $0.258, $0.58 with one (Sume pricing page, as of 2026-10-08). The docs do not list a separate price for the preview stage in the pages cited here, so the table covers render spend only.

Is the extra render worth it?

The Standard path is described as the fastest Sume execution path, so a Standard render is a fast way to hear pacing and lip movement before committing to Max, which the docs call the highest quality tier with slower turnaround. The check pays off only when a pacing or wording problem is likely. If the first-frame still already looks right and the script is final, go to Max directly and keep the $3.68.

Practical notes

Idempotency. The docs examples send an Idempotency-Key header on every create call. Use one key per intended job and reuse it only when you retry the same request. A network timeout followed by a fresh submit with a new key is the one path that can create, and bill, a second job. Keep keys human-readable, such as the campaign and scene, so a support lookup is easy.

Quality tiers. quality accepts standard, plus and max. Plus is the default when you omit it. Standard is the fastest Sume execution path, and Max is the highest quality tier with slower turnaround. Because the three differ in both price and speed, decide the tier per stage of your workflow: a quick pass to confirm wording, then a final render once the script is settled.

Output format. Avatar video output is 720p at this time, and the aspect ratio defaults to 9:16 with 1:1, 3:4, 4:3 and 16:9 also accepted. Choose the ratio in the request rather than cropping afterward, since a crop throws away part of a frame you paid for by the second.