Product turntable 1:1: Wan 3.0 draft at 480p, final at 1080p
An 8-second square turntable on Wan 3.0 costs $0.50 at 480p and $2.00 at 1080p on Sume, so five drafts plus one final is $4.50, not six finals.

Draft the motion at 480p and spend the 1080p price once. On wan-3.0, an 8-second clip costs $0.50 at 480p, $1.00 at 720p and $2.00 at 1080p. Five 480p drafts and one 1080p final come to $4.50 against $12.00 for six 1080p tries. Source: Video generation, read 2026-10-06.
Wan 3.0 lists 1:1, so the square crop is native. Keep the prompt and the first-frame photo identical between draft and final; the motion will not match frame for frame, but the staging and look do.
What does each rung cost?
Eight seconds, 1:1.
| Model id | Resolution | Length | Sume price | Note |
|---|---|---|---|---|
| wan-3.0 | 480p | 8 s | $0.50 | draft |
| wan-3.0 | 720p | 8 s | $1.00 | |
| wan-3.0 | 1080p | 8 s | $2.00 | final |
What does the request look like?
Only resolution changes between draft and final.
curl -sS -X POST https://api.sume.com/v1/videos \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "wan-3.0",
"prompt": "A white sneaker rotates slowly on a pale grey plinth, soft studio light",
"duration": 8,
"resolution": "480p",
"aspect_ratio": "1:1"
}'Sources
Related posts
More in Use cases
- Product video for ecommerce: a white-background photo to 9:16
Turn a white-background product photo into a 5-second vertical scene with POST /v1/videos, seedance-2 and an image_url input reference.
- Raw-to-plated recipe clip: first and last frame on Sume
Pin the raw-ingredients photo as the first frame and the plated dish as the last. Wan 3.0, Omni Flash 1.1 and H3 take both; the 8-second prices are inside.
- Real-estate agent, 25 listings a month: staged photos and voiceover
25 listings with six AI-edited photos, a voiceover and a music bed cost about $14.60 a month on Sume. Unit prices and the sum.
- AI listing video disclosure line: put it in the Sume output schema
Carry the AI disclosure and the original-photos link with each listing video: a typed output_schema field, what input does not carry, and a check.
Written by Sume