Google Autocomplete Keywords — with Relevance Scores
Pricing
from $1.00 / 1,000 results
Google Autocomplete Keywords — with Relevance Scores
Turn a seed keyword into the phrases people actually type, straight from Google's autocomplete, with Google's own relevance score on every suggestion. Alphabet, question and comparison expansions for depth. Web, YouTube, Images and Shopping. You set the language and country. Keyless.
Pricing
from $1.00 / 1,000 results
Rating
0.0
(0)
Developer
Farhan Febrian Nauval
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
10 days ago
Last modified
Categories
Share
Turn one seed into the phrases people actually type, straight from Google's autocomplete — and with Google's own relevance score on every suggestion, not a score invented here.
Keyless. No login, no browser, no proxy, no API key.
What you get
| Field | Example |
|---|---|
keyword | budget tracker google sheets |
relevance | 601 — Google's own ordering weight |
seed / query | budget tracker / budget tracker how |
expansionToken | how (null for the seed's own query) |
rankInQuery | 2 — position within that query's suggestions |
dataset / language / country | web / en / us |
Measured on one seed: budget tracker with the questions expansion returned
67 unique keywords from 14 requests, every one carrying a relevance score.
Google returns 15 per query. Depth comes from asking differently
Every populated dataset returned exactly 15 suggestions, so 15 is treated as a cap rather than a coincidence — and the actor says so in the log when a run hits it on every seed.
| Expansion | Queries per seed | What it surfaces |
|---|---|---|
none | 1 | the plain 15 |
alphabet | 27 | the widest net — a to z appended |
questions | 14 | how / what / why / when — content and FAQ work |
prepositions | 14 | for / with / vs / near — intent and use cases |
comparisons | 9 | vs / alternative / better than — competitors |
Suggestions are de-duplicated across an expansion, because the seed itself comes back under
almost every token. The first sighting wins, so rankInQuery and relevance always belong
to the query recorded on the row.
Set the language and country, or your server sets them for you
This is the one input worth reading twice. With hl/gl unset, Google answers for
wherever the request came from. Same query, same second, three locales:
| Setting | First suggestions |
|---|---|
| unset, from an Indonesian connection | budget tracker adalah, budget tracker template |
hl=en&gl=us | budget tracker template, budget tracker google sheets |
hl=de&gl=de | budget tracker app, budget tracker excel, budget tracker notion |
Both are sent on every request and recorded on every row, so two runs for two markets stay comparable.
Four datasets, because only four of Google's eight do anything
ds= selects a vertical. Compared against the web result set for the same query:
| Dataset | Result | Offered? |
|---|---|---|
| Web | the baseline, 15 suggestions | yes |
| YouTube | 15 suggestions, 12 differ | yes |
| Images | 15 suggestions, 6 differ | yes |
| Shopping | 7 suggestions, 4 differ | yes |
| News | 15 suggestions, 0 differ — accepted and silently ignored | no |
| Books, Video, Recipes, Products | empty | no |
A "news keyword research" mode would have shipped returning plain web suggestions while looking like it worked. Only the datasets that demonstrably change the answer are offered, and the rest are named here so nobody re-adds them.
This is not the results page
Autocomplete is the endpoint a browser calls while you type. It answers in well under a kilobyte and needs no proxy, which is why a run of this costs almost nothing. It reports what Google suggests, which is a signal about demand — it is not a rank tracker and does not claim search volume.
