What it costs to finish 100 holiday ads: captions, trim, timeline
Sume's documented prices for captions, trim, timeline render and music, added up for 100 finished ads, plus what the total leaves out. Confirm live first.

Finishing 100 ads, with one trim, one caption job, a one-minute-or-shorter timeline render and one music track each, comes to about $44.50 at the prices in Sume's docs: $0.02 + $0.20 + $0.10 + $0.125 = $0.445 per ad. That excludes the video generation itself, which is billed per model at provider list times 1.25. Each page says to confirm live prices in GET /v1/catalog, so treat this as arithmetic and not a quote.
What are the per-step prices?
| Step | Endpoint | Documented price | x 100 ads |
|---|---|---|---|
| Trim | POST /v1/video-trim | $0.02 per job | $2.00 |
| Captions | POST /v1/video-captions | $0.20 per job, videos up to 60 s | $20.00 |
| Timeline render | POST /v1/timeline-1.0/render | $0.10 per output minute, rounded up | $10.00 (all under 1 min) |
| Music | Music 1.0 | $0.125 per generation | $12.50 |
| Total | $44.50 |
Where does the arithmetic stop being true?
- A render longer than one minute is billed for each started minute, so a 61-second ad is two.
- A caption job covers videos up to 60 seconds. Longer videos are outside the quoted price.
- Reusing one music track across ads removes that line. Generating a track per ad is the high case.
- Timeline planning with
POST /v1/timeline-1.0/planis unbilled, so check the estimate before a batch. - Retries with the same
Idempotency-Keydo not create a second job, but a new key is a new charge.
How do I check it before spending?
Call GET /v1/catalog with your key and compare each line to the table. Then dry-run the plan step for a sample timeline and read estimated_cost_usd_micros in the plan response. The generation step is the big variable: choose the model and clip length with GET /v1/videos/models, multiply by the resolution price, and add 25 percent, which is how Sume bills provider list.
curl -X POST https://api.sume.com/v1/timeline-1.0/plan \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"audio": { "mode": "silence", "duration_seconds": 15 },
"video": [
{ "source_url": "https://media.sume.com/artifacts/artf_demo/ad.mp4", "start": 0, "duration": 15 }
]
}'Which steps can I skip?
Not every ad needs every step. A clip that already has burned-in text does not need the $0.20 caption job, which saves $20.00 across 100 ads. A clip that is already the right length does not need the $0.02 trim. If a bed of music is shared across a family of ads, the $12.50 line becomes $0.125. The cheapest finishing path is the one that avoids work the generation step already did.
What does it leave out?
It leaves out generation, speech-to-text if you transcribe separately, any storage you keep outside Sume, and your own time reviewing 100 clips. For the generation side, see the per-SKU cost post. A holiday test usually costs less if you finish ten ads first, read the totals, and then scale.
Sources
Related posts
More in Pricing
- Are flat Sume timeline, trim and filter prices ceilings or fixed fees?
Flat prices for Sume timeline, compose, trim, filter and audio detach are reserved up front and captured at actual compute, never above the reservation.
- Veo 3.1 in Flow credits vs the Gemini API: cost of an 8-second clip
Flow charges 10, 20 or 100 credits for an 8-second Veo 3.1 Lite, Fast or Quality clip; the Gemini API lists $0.40 to $3.20. Sume does not list Veo.
- Veo 3.1 Fast 20 credits vs Quality 100 in Flow: a draft ladder
Flow charges 100 credits for Veo 3.1 Quality and 20 for Fast. Draft count per final, why the free daily credits cannot buy a Quality clip, and the Sume way.
- Veo 3.1 Lite in Flow: 10 credits, 5 on Ultra. How many drafts?
Flow's credits page prices Veo 3.1 Lite at 10 credits, or 5 for Ultra. What that buys per plan, and a cheap draft step before you spend on a final.
Written by Sume