Keyword Research — Google, YouTube, Amazon & Bing Autocomplete

Turn a seed keyword into hundreds of real long-tail keywords and questions people type into Google, YouTube, Amazon, Bing, DuckDuckGo and Google Shopping.

Each seed is expanded with a–z / 0–9, question words (how, what, why…) and buyer-intent modifiers (best, cheap, vs, near me, price, alternative…). Every keyword comes with:

search intent (informational / commercial / transactional / navigational), question flag, word count, which sources suggested it, how many sources agree, best autocomplete position, and the query that surfaced it.

How to run it in 3 steps

1. Add your input. In Seed keywords paste seed keywords, one per line — e.g. coffee maker. The form is already filled with a working example, so you can skip this step for a first try.
2. Press Start. The prefilled run returns 30 keywords in about 4 s and costs about $0.090. Set Max results (cost cap) to cap the cost of bigger runs; you only pay for keywords actually delivered.
3. Get the data. Open the Output tab and export JSON, CSV or Excel — or run it from the API, Make, Zapier, n8n or an AI agent (see below).

Features

• 6 sources in one run, merged and deduplicated — keywords suggested by several engines are ranked first.
• Fast: ~250 autocomplete queries per seed in a few seconds (2 seeds → 1,879 keywords in 5 s in our test).
• Ready to use: intent and question tags for content plans, PPC ad groups and Amazon listing keywords.
• Pay per keyword: $3 per 1,000 keywords. Cap it with maxKeywordsPerSeed.

Use cases

• SEO & content: find questions to answer and long-tail topics to rank for.
• YouTube SEO: titles and tags people actually search for.
• Amazon sellers: backend keywords and listing copy from Amazon's own suggestions.
• PPC: build ad groups by intent; find negative keywords.

Input

{
  "seedKeywords": ["coffee maker", "crm software"],
  "sources": ["google", "youtube", "bing", "amazon"],
  "alphabet": true,
  "questions": true,
  "modifiers": true,
  "country": "us",
  "language": "en",
  "maxKeywordsPerSeed": 300
}

Output

Real output (default input)

First 2 of 30 records from a run with the prefilled input (3.3 s on a test machine; long values shortened here):

[
  {
    "keyword": "best coffee maker",
    "seed": "coffee maker",
    "isQuestion": false,
    "intent": "commercial",
    "wordCount": 3,
    "length": 17,
    "sources": [
      "google",
      "youtube",
      "bing"
    ],
    "sourceCount": 4,
    "bestPosition": 1,
    "foundVia": [
      "best coffee maker",
      "top coffee maker"
    ],
    "language": "en",
    "country": "us"
  },
  {
    "keyword": "best coffee maker 2026",
    "seed": "coffee maker",
    "isQuestion": false,
    "intent": "commercial",
    "wordCount": 4,
    "length": 22,
    "sources": [
      "bing",
      "amazon",
      "google"
    ],
    "sourceCount": 4,
    "bestPosition": 1,
    "foundVia": [
      "coffee maker 2",
      "best coffee maker"
    ],
    "language": "en",
    "country": "us"
  }
]

{
  "keyword": "best coffee maker 2026",
  "seed": "coffee maker",
  "intent": "commercial",
  "isQuestion": false,
  "wordCount": 4,
  "sources": ["bing", "amazon", "google", "youtube"],
  "sourceCount": 4,
  "bestPosition": 1,
  "foundVia": ["coffee maker 2", "best coffee maker"]
}

Autocomplete shows what people search for, not search volumes — combine with your favourite volume tool.

Pricing

• $3.00 per 1,000 keywords ($0.003 per keyword).
• The prefilled input returns 30 keywords → $0.09.
• Example: 1,000 keywords → $3.00; 10,000 → $30.00. Set Max results (cost cap) to limit any run.

• Duplicates across sources are free.
• Your Apify spending limit is respected exactly: the actor stops charging and finishes cleanly when it is reached. Apify platform usage (compute, proxy) is included in the price.

Use with AI agents (MCP), LangChain, RAG & the API

This actor is a ready-made tool for AI agents: an LLM can call it, wait for the run and read clean JSON back.

MCP server (Claude Desktop, Claude Code, Cursor, VS Code, any MCP client) — add Apify's hosted MCP server with this actor enabled as a tool:

{
  "mcpServers": {
    "apify": {
      "url": "https://mcp.apify.com/?tools=torix33/keyword-research-autocomplete",
      "headers": { "Authorization": "Bearer <APIFY_TOKEN>" }
    }
  }
}

LangChain / LangGraph (pip install langchain-apify, set APIFY_API_TOKEN):

import json
from langchain_apify import ApifyActorsTool, ApifyWrapper
from langchain_core.documents import Document

# 1) give the actor to an agent as a tool
tool = ApifyActorsTool("torix33/keyword-research-autocomplete")

# 2) or load results as Documents for a RAG index
loader = ApifyWrapper().call_actor(
    actor_id="torix33/keyword-research-autocomplete",
    run_input={"seedKeywords": ["coffee maker", "crm software"], "sources": ["google", "youtube", "bing", "amazon"], "alphabet": True, "questions": True, "modifiers": True, "country": "us", "language": "en", "maxKeywordsPerSeed": 300},
    dataset_mapping_function=lambda item: Document(page_content=json.dumps(item, ensure_ascii=False), metadata={"url": item.get("url")}),
)
docs = loader.load()

REST API — one synchronous call, dataset items in the response:

curl -X POST "https://api.apify.com/v2/acts/torix33~keyword-research-autocomplete/run-sync-get-dataset-items?token=<APIFY_TOKEN>" \
  -H "Content-Type: application/json" \
  -d '{"seedKeywords": ["coffee maker", "crm software"], "sources": ["google", "youtube", "bing", "amazon"], "alphabet": true, "questions": true, "modifiers": true, "country": "us", "language": "en", "maxKeywordsPerSeed": 300}'

Also works with the Apify Python/JS clients, Make, Zapier, n8n, Google Sheets, webhooks and schedules. Export as JSON, CSV, Excel, XML or RSS.

RAG tip: Give an agent the deduplicated keyword list with intent tags and let it cluster them into a content plan or PPC ad groups.

Limitations

• Autocomplete has no search volumes; keywords suggested by several engines are ranked first as a popularity signal.
• Suggestions differ by country and language — set them to match your market.
• At most maxKeywordsPerSeed keywords per seed.

FAQ

Is it a Keywordtool.io alternative? Yes — it collects autocomplete suggestions from several engines in one run at $3 per 1,000 keywords.

Does it return search volume? No. Autocomplete data has no volumes; keywords suggested by several engines are ranked first as a popularity signal.

Can I get question keywords? Yes. Turn on questions for who / what / how / why style suggestions.