set up treg — https://treg.to/llms.txt
Using treg, find 25 Instagram fitness creators in the US with 50k to 500k followers and engagement above 3%. Show me the price first. Then pull each profile and its last 12 posts, and give me a CSV with username, followers, engagement_percent, category, whether the account is private, and likes and comments on the sample.
influencers.club searches Instagram, TikTok, YouTube, X and Twitch separately, and the filter set changes with the platform.
Follower range, engagement floor and country are enforced server-side. A plain-language brief drops constraints it cannot map.
Discovery bills per creator returned, so the limit you set is the bill. The table below shows the live rate.
The discovery row is a snapshot. A profile call returns today's follower count and the bio.
Prices are the provider’s own rate, read from the catalog when this page loads, with $0.000 added by treg.to. Success rates are treg.to’s own served calls over the last 30 days.
| # | Step | What the agent asks | Provider used | Price | Success rate |
|---|---|---|---|---|---|
| 1 | Search creators by nicheStructured discovery: exact follower, engagement and country filters. Billed per creator returned; a zero-match page costs nothing. | filtered search by bio keyword, follower range, engagement floor and country | influencers.club2 providers do this step | $0.00598 per result | not yet measured |
| 2 | Pull each profileThe cheapest profile route in the catalog. Runs once per creator from the discovery list. | today's follower count, bio, category and private flag for one handle | $0.001 per found | 100% (115784 calls) | |
| 3 | Sample recent postsRuns once per creator. Likes and comments over followers is the engagement check the discovery row cannot give you. | the last 12 posts with likes and comments, by the numeric user id from the profile | $0.001 per found | 100% (24720 calls) |
Run on 2026-09-14, 25 creators in.
One discovery call matched 153 creators and returned the 25 requested, billed per creator returned. Twenty-five profile pulls followed, one per handle, and every one resolved; the post sample then answered for 24 of them, and 19 had posts to count. The CSV has the discovery snapshot and the same-day profile count side by side, which is how you spot a stale row. Usernames are removed from the published CSV because they identify real people; your own run returns them.
treg.to holds the provider keys. Neither you nor the agent sees them.
The provider's own rate, $0.000 markup, from a prepaid balance.
Charged per call. $1.00 free per new team, no card to start.
Already pay Hunter? Register it and those calls are never metered.
Another provider is a different word in the prompt, not a new integration.
No SDK, no OAuth dance per vendor, no seats.
A combination that matches nobody returns zero rows and costs nothing. Widen one filter at a time.
The plain-language brief maps what it can and silently drops the rest. Put every hard limit in filters and use the brief for the fuzzy part.
The discovery index lags. A profile pull on a renamed handle misses; the miss is free on this route.
Creator location comes from language and hashtags. Verify before a geo-targeted campaign.
Per creator returned, at the live rate in the table above. The limit you pass is the bill; the total match count is free.
Yes. Exact filters go in the filters object and the niche description in nlp_search. The response says which parts of the brief were applied.
Set the platform in the same discovery call. Swap the profile step for the matching platform's profile route.
Discovery rows are a snapshot. The profile call returns today's follower count, the bio and whether the account went private.