Six-scene 30-second avatar ad: approve six stills, then $5.52-$16.50

For a multi-scene avatar ad on Sume, the preview stage returns one first-frame still per scene, so you can approve a six-scene, 30-second plan before paying for the render. The final render then costs $5.52 at Standard, $7.35 at Plus or $16.50 at Max.

What the preview returns

Create the preview with ordered video_inputs and read scene_previews[], one still per input scene, plus preview_image_url for scene 0. For multi-scene previews with a shared scene, later stills are pose-anchored continuations of the first frame. The docs prefer resource_status and job_status over the legacy status field.

Changing your mind

Edit and regenerate the stills with POST /v1/avatar-video-previews/:id/regenerate, which reuses the stored request. If you change a structural field, meaning script, video_inputs, avatar_handle, scene or aspect_ratio, create a new preview. Changing only quality at generate-video does not need one.

The docs do not list a price for the preview stage on the pages cited here, so confirm it on the pricing page before running many previews.

• Same duration window as a direct render: 4 to 60 seconds in total.
• Captions stored on create are applied at generate-video.
• Media inputs are public HTTPS URLs.

Why approve stills first

With six scenes, one bad composition spoils the whole video. Reviewing six stills before a $16.50 Max render is cheaper than discovering the problem afterward. A product or scene reference that fails to land is visible in the stills.

Practical notes

Media inputs. Any media field, whether product_image, scene.image_url or an avatar image_url, must be a fetchable public HTTPS URL. Sume rejects localhost, private-network and non-HTTPS addresses before it submits anything, so a broken link fails fast instead of consuming a render. Host reference images where Sume can fetch them and keep them available until the job finishes.

Reading results. A completed result can include public media.sume.com video artifacts, and for avatar videos also public-safe preview fields such as preview_image_url and scene_previews. You can list or read finished videos with GET /v1/avatar-videos and GET /v1/avatar-videos/{id}. Store the job id and the video id together so a billing line can be traced back to a creative.

Reusable avatars. An avatar is created once, for a flat $0.95, and then referenced by its avatar_handle on every later request. Sume normalizes a leading @ away and stores the handle without it. Treat the handle as a stable identifier in your own system, and keep one record per handle noting who the avatar represents and what it may be used for.

Job lifecycle. Every Sume avatar request is job-backed. You submit, store the job id, and poll GET /v1/jobs/{id}/status until it completes, then read GET /v1/jobs/{id}/result. The shared lifecycle also lets you wait with sync or subscribe mode for a limited time instead of polling, and the result carries Sume-hosted artifacts rather than provider URLs, so you never handle a provider queue id. Plan your client around the job, not around a single blocking response.