75-second founder story: 3 jobs on Wan 3.0 or Seedance 2.5
75 seconds of founder story on Sume: 3 jobs, $9.3750 on Wan 3.0 and $43.3350 on Seedance 2.5 at 720p. 480p and 1080p priced too.

A 75-second founder story is more than one job on Sume: Wan 3.0 and Seedance 2.5 each stop at 30 seconds per request, so it takes 3 jobs of 25, 25, 25 seconds. At 720p and 9:16 the set costs $9.3750 on Wan 3.0 and $43.3350 on Seedance 2.5.
The limits come from Sume's video generation docs (read 2026-10-06): seedance-2.5 accepts 4 to 30 seconds at 480p, 720p and 1080p, and wan-3.0 accepts 2 to 30 seconds. A founder story up to 30 seconds therefore needs no stitching.
What does a 75-second founder story cost by model and resolution?
Both prices below are computed from Sume's rate card on 2026-10-06 for a 9:16 request. Wan 3.0 is a per-second rate by resolution; Seedance 2.5 is priced by video tokens, so its price scales with the pixel count too.
| Model and resolution | Jobs | Total |
|---|---|---|
| Wan 3.0, 480p | 3 | $4.6875 |
| Seedance 2.5, 480p | 3 | $20.15077 |
| Wan 3.0, 720p | 3 | $9.3750 |
| Seedance 2.5, 720p | 3 | $43.3350 |
| Wan 3.0, 1080p | 3 | $18.75 |
| Seedance 2.5, 1080p | 3 | $106.61625 |
How do I send it?
Submit with POST /v1/videos, send an Idempotency-Key so a retry returns the original job, and poll the polling_url or pass an HTTPS callback_url. Send 3 requests, one per segment, and join the clips afterwards with a Timeline render.
curl -X POST "https://api.sume.com/v1/videos" \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: clip-wan-3.0-25s-001" \
-d '{
"model": "wan-3.0",
"prompt": "A product on a desk, slow push-in, natural light",
"duration": 25,
"resolution": "720p",
"aspect_ratio": "9:16"
}'What should I check first?
Prices change when providers change theirs, so the table is a snapshot, not a quote.
- Read
supported_durationsandsupported_resolutionsfromGET /v1/videos/modelsbefore you pick a length. - Sume reserves the provider list price times 1.25 at submit;
usage.coston the finished job is the billable amount. - Segments are separate generations, so keep the same prompt scaffolding and reference images in each to keep the founder story consistent.
Sources
Related posts
More in Pricing
- 8 explainers at 3,000 characters: MAI-Voice-2.1 $0.53 vs Sume $1.20
Eight 3,000-character voiceovers is 24,000 characters: $0.53 on MAI-Voice-2.1 at $22 per million, $0.36 on Flash, $1.20 on Sume at $0.0475 per 1,000.
- 8 video ads of 15 seconds on Wan 3.0 at 480p: $7.50
8 separate 15-second ads on Sume Wan 3.0 at 480p, $0.9375 each, $7.50 in total. One job per ad, with a request example and the 30-second limit.
- 8 video ads of 15 seconds on Wan 3.0 at 720p: $15.00
8 separate 15-second ads on Sume Wan 3.0 at 720p, $1.8750 each, $15.00 in total. One job per ad, with a request example and the 30-second limit.
- 8 YouTube chapter cards: GPT Image 2.5 low is $0.004 each at 1280x720
Eight 16:9 chapter cards at 1280x720 cost $0.032 on GPT Image 2.5 low via Sume, against $0.20 to $0.80 on flat-price models. The request and the math.
Written by Sume