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
- FLUX.2 klein API price: $0.014 plus per megapixel, and Sume
BFL's page lists FLUX.2 klein 4B at $0.014 + $0.001 per MP and 9B at $0.015 + $0.002 per MP. Sume's catalog lists FLUX.2 pro and flex, not klein.
- Gemini image API price per image: Lite, Flash and Pro tiers
Google lists Gemini 3.1 Flash Lite Image near $0.0336 per 1K image, Flash from $0.045 to $0.151, Pro $0.134 to $0.24. How to read the per-image line on Sume.
- Gemini Omni Flash 1.1 at $17.50 per 1M tokens: dollars per second
Google prices Omni Flash 1.1 video output in tokens, about $0.10 a second at 720p. What that means per clip, and how Sume's per-second rate is built.
- Gemini Omni Flash 1.1 clip cost matrix: 3 to 10 seconds, 360p to 4K
A lookup table for Gemini Omni Flash 1.1: list cost per clip for 3, 5, 8 and 10 seconds at 360p, 720p, 1080p and 4K, with Sume's list x 1.25 beside it.
Written by Sume