Weekly TikTok trend research: 4 searches a week cost $20.80 a year
Sume's trending-video search is $0.10 per accepted call. Four searches a week for 52 weeks is 208 calls, $20.80. Windows, limits, and what comes back.

Each accepted call to POST /v1/trending-videos/search reserves and captures $0.10 of Sume usage. Four searches a week for a year is 4 x 52 = 208 calls, and 208 x $0.10 = $20.80. The endpoint returns ranked public TikTok video metadata for research. It is not a generation model and it does not return video files.
What a weekly routine looks like
A trend routine is a fixed set of questions, asked on the same day, with the same window. Pick the queries once: your brand, a competitor, a product category, and one creator or hashtag. Run them with window: "this-week" and compare the lists from week to week.
| Field | Production behaviour |
|---|---|
query | Required; brand, product, creator, or keyword, up to 200 characters |
window | yesterday, this-week, this-month, last-3-months, last-6-months, all-time |
limit | 1 to 50, default 10 |
region | Optional two-letter country code |
summary_mode | none (default), metadata, or transcript (returns metadata plus an unsupported warning) |
Cost by cadence
The rate is flat per call, and summary_mode: metadata is in the same price. Repeat browse calls can be served from cache, so they do not hit the upstream source again.
| Searches per week | Calls per year | Year total |
|---|---|---|
| 1 | 52 | $5.20 |
| 4 | 208 | $20.80 |
| 10 | 520 | $52.00 |
What you get back
Each entry has the canonical public watch URL, an optional cover thumbnail, description, creation time, region, author handle and nickname, metrics, relevance, and scores. With a summary mode, it adds a light summary. The response does not include raw TikTok CDN video URLs.
That sets the next step. Use the list as research: open the watch URLs, note the hooks, and decide what to make. The docs say the endpoint does not return downloadable source files for face swap or captions. Use your own media as input to Sume's other tools.
Turning a list into a decision
A search is cheap, so the discipline is in what you do with the list. Write down three things for each week: which hook patterns repeat, which formats show up across several authors, and which sounds or on-screen texts recur. Compare against last week and drop anything that did not repeat. Two weeks in a row is a trend, one week is an accident.
Keep the query text stable between weeks. The relevance and scores fields are only comparable if the query is the same. If you change a query, count it as a new series. When the idea is picked, hand it to a generator: Sume's video, image, and avatar families all take your own public HTTPS media as inputs, and a Format can run the whole piece.
Production versus the rebuild
The no-query browse feed with a higher limit is on for the dev host and stays off in production until a flag is set. In production, query is required and limit is 1 to 50. If your routine needs a no-query browse, check which host you are calling before you plan the budget. Confirm the live price in GET /v1/catalog.
Sources
Related posts
More in Use cases
- Weekly TikTok trend sweep: 3 regions x 4 keywords is $1.20
Loop four keywords over US, GB and KR with Sume trending search: 12 calls, $1.20 a week. A short Python script and a month of cost.
- Which caption style wins? Test slam, punch, tiktok-green
Burn three caption styles onto one clip for $0.60 and compare them. Latin text works on all three; Korean text is rejected on these styles. Runnable loop.
- Vertical 9:16 Seedance ad at 720p: $1.512 on Mini, $4.6224 on 2.5
An 8-second 720p vertical ad costs from the Mini price to the Seedance 2.5 price on Sume. All four tiers at 6, 8, 12 and 15 s, and the 720x1280 frame size.
- Wine tasting invite video: Wan 3.0, 9:16, 12 s, audio reference
A 12-second vertical invite on Wan 3.0 costs $0.75 at 480p and $1.50 at 720p on Sume, and takes up to 5 audio references. Age gates and limits.
Written by Sume