Captioning 250 holiday clips costs $50.00 at Sume's current estimate

A Sume caption job is $0.20 for clips up to 60 seconds at the current fixed estimate. What 100, 250 and 500 clips cost, and how to confirm the live price.

4 min readSume
All posts

At the current fixed estimate, each accepted standalone caption job reserves and captures $0.20 for a video of up to 60 seconds, so 250 holiday clips cost $50.00 in caption jobs. The docs mark that as an estimate and point to GET /v1/catalog and OpenAPI for the live price, so use the arithmetic below for planning and check the catalog before a large run.

Cost table

The multiplication is simple, and the limits are what matter: the price covers clips up to 60 seconds, and inline avatar-video captions are priced separately as an add-on in that estimate. A holiday campaign tends to produce many short cuts of the same offer, which is why the count grows faster than the footage: five cuts of fifty products is already 250 jobs.

Keep the figures in a planning sheet with a column for the live catalog price, so that if the number moves you change one cell and every row updates. The docs call the $0.20 a fixed estimate, which is a reason to treat it as a budget line and not as a quote.

Caption job cost at $0.20 each, read 2026-10-08
ClipsCaption jobsCost at $0.20
5050$10.00
100100$20.00
250250$50.00
500500$100.00

Steps

Do the check in this order so a price change does not surprise you.

  • Read the live caption price from GET /v1/catalog and compare it with $0.20.
  • Confirm every clip is 60 seconds or shorter; longer clips are outside the stated estimate.
  • Send one job per clip with its own Idempotency-Key, named after the clip, so a retry does not charge twice.
  • Use restyle with source_caption_id for extra looks of the same clip, which is still a render at the same price.

What Sume does not do

Sume does not give a bulk discount on captions in the pages we read, and the docs do not describe a batch caption endpoint, so 250 clips means 250 requests. Spread them over time or in a small loop with backoff, and read the status of each job before you start the next phase of your pipeline. Inline captions on an avatar video are not a video_caption resource and are priced in the avatar estimate, so do not add them to this table.

Failed or canceled jobs are a second reason to read your usage after a run. The estimate describes an accepted job, so compare the number of accepted jobs with your spreadsheet of expected clips, and reconcile any gap before you report a campaign cost to anyone. This post does not assert what happens to the charge on a failed caption job, because the page we read does not say.

Budget habit

A good habit for a seasonal push is to set a ceiling before the work starts: the number of clips times the live price, plus a margin for reruns. If a reviewer asks for a different style on every clip, that is a second set of jobs at the same price, so ask for the look decision early and run it on three sample clips first.

Sources

Related posts

More in Use cases

All Use cases posts

Written by Sume