Use case, Rank tracking

Rank tracking API for your agent. One call per keyword.

Send a keyword, a country and your domain. Read organic position and ranking URL back. Your agent picks the provider, and you pay per call.

Give this to your agent
set up looot for Rank tracking API - https://looot.ai/use-cases/rank-tracking-api/skill.md

The short answer

The short answer

Rank tracking API for an agent: it sends a keyword, a country and your domain to a catalog endpoint and reads organic position, ranking URL and title back. Several providers sell the call, so the agent tries the cheapest first. You pay per call, and a failed call costs nothing.

  • Organic position
  • Ranking URL
  • Title and snippet
  • Up to 100 results
  • Device and location

The job

What the Rank tracking API gives your agent

You want one number: where your page sits on Google for a keyword today. A rank check sends the keyword with a country, reads the organic results until it finds your domain, and reports the position and the URL that ranks.

The difference that matters is depth. A plain results call returns about ten organic results, so a page in position 40 takes four more calls. The SearchAPI.io rank tracking endpoint and Serper return up to 100 organic results in one call, which is how most rank checks are done. DataForSEO returns either a plain ranked list or the full page with featured blocks.

You give

a keyword, a country and your domain

project management software

You get

  • Organic position
  • Ranking URL
  • Title and snippet
  • Up to 100 results
  • Device and location

Providers, cheapest first

What actually differs between providers

Today the price runs from $0.0009 to $0.0040 across 6 endpoints. The dearest costs about 4.4 times the cheapest. Price is only one difference. Each entry below says what that endpoint takes or returns that the others do not.

Sample calls

The request and what comes back

Each run is one POST to /v1/runs with an endpoint id and an input. These are illustrative calls with generic values. The run's result holds the provider's own fields.

Request
{"endpointId":"searchapi-io-google-rank-tracking","input":{"q":"project management software","gl":"us","num":100},"wait":30}
ResponseSample output
// POST /v1/runs, then read run.status and run.result
// result: returns up to 100 organic results in one call, for desktop or mobile, in any Google domain, language and location

The prompt

Copy one prompt, give it to your agent.

Edit the names and numbers, paste it, and the agent runs the job and shows the cost.

  • One run is one keyword.
  • 1 step across 4 providers.
  • Runs on demand, whenever you ask.
Prompt: Rank tracking API
Use looot to find where example.com ranks on Google in the United States for project management software, checking the top 100 results, and return the position, the URL that ranks and the three domains just above it. 1. Set up https://looot.ai/skill.md. 2. Search the catalog for each step and check its price before you call. 3. Run the cheapest endpoint that fits. 4. Show the results as a table and the total cost.

Give this to your agent
Setup command
set up looot for Rank tracking API - https://looot.ai/use-cases/rank-tracking-api/skill.md

Before you start

Settle these before the first run

  • Fix the market. Set the country, the language and the device, and keep them the same between checks, or the positions will not compare.
  • Check deep enough. If your domain is not in the results you asked for, the answer is not in the top 100, not that it does not rank.
  • Store the date with each position. A rank is a snapshot, and following it day after day needs scheduled runs, not available yet.
  • One SearchAPI.io endpoint bills each search even when no results come back. Check the endpoint page before a long keyword list.

FAQ

Questions people ask

It is an endpoint that reads Google's organic results for a keyword in a given market and gives your agent the position of a domain in them. Your agent sends the keyword, the country and the domain, and gets the position and the ranking URL back.

Ask your agent to run the keyword through the rank tracking endpoint with your country and up to 100 results, then find your domain in the list. The answer is a position and a URL, or not in the top 100.

Up to 100 with the SearchAPI.io rank tracking endpoint or Serper. The other search endpoints return about ten per call, so a deep check needs one call per page.

Yes. Set the device, the country and the language in the call. Positions differ between them, so your agent should report the market it checked with every number.

Each run is one check at one moment. Store each answer with its date and compare. Running the checks on a timer needs scheduled runs, not available yet.

The Google SERP API page returns the whole results page for a query, with its parsed blocks. This page answers one question, where a domain ranks, so it favours endpoints that return 100 results in one call.

You pay per call, and the price depends on the provider your agent picks. This page reads the cheapest live price from the catalog and shows no number when the catalog is unreachable.

No. A call that fails at the provider costs nothing, and your agent can retry it or send it to another provider.

No. One looot key reaches every provider in the catalog. You top up once, and each call is billed at the price shown before it runs.

Send a POST to /v1/runs with the endpoint id, the input and a new idempotency key, and your looot token in the Authorization header. With wait set to 30, the answer comes back in the response when the run ends within 30 seconds. Otherwise poll GET /v1/runs/<runId>.

That needs scheduled runs, not available yet. Run it by hand whenever you want fresh results.

No. looot bills per call, and nothing runs while your agent is idle.
For agents
use case
Rank tracking API
run
keyword
schedule
on demand
step
Check the position: searchapi-io serper dataforseo anyapi
setup
https://looot.ai/use-cases/rank-tracking-api/skill.md
llms.txt
https://looot.ai/llms.txt
updated
2026-10-04

Try Rank tracking with your own agent.

Start your workspace, top up, and paste the prompt into the agent you already use.