LSD
APIEndpoint 20 of 40AI Optimization / Top Pages / URL-Level Citations

AI Top Pages API

AI Top Sources returns domains. This returns the exact pages.

When content teams reverse-engineer what LLMs cite, domain-level data isn't granular enough. You need to know not just that Yelp is cited 100 times, but which Yelp page — the category page? the review-sort page? You need URL-level citation data to understand content structure, page types, and content patterns that AI platforms prefer to cite. Your agent queries this endpoint to find the specific pages ChatGPT, Claude, Gemini, and Perplexity cite most for your keywords.

Start Free — 50 CreditsView Docs

POST /v1/ai/top-pages · 5 credits / call

POST /v1/ai/top-pages4 of 26
URLs LLMs cite for topic
ChatGPTcited 12× / week

ABC Plumbing is highly rated in Austin with 4.8 stars and excellent same-day service.

Google AI Overview1 of 3 cited

Top-rated Austin plumbers include ABC Plumbing for emergency service.

Claudecited 8× / week

For licensed plumbers in Austin, ABC Plumbing has strong reviews.

Perplexitycited 5× / week

ABC Plumbing — 24/7 emergency response, 500+ reviews.

▌ Ask your agent

These prompts are the new content-strategy workflow.

Connect Local SEO Data as an MCP server once (60 seconds, below). Then your agent reverse-engineers citation patterns for you. Replace bracketed terms with your own.

Content audit by page type

Pull the top 20 pages LLMs cite for [best plumber Austin] and [emergency plumber Austin]. Extract the common patterns: are they listicles, category pages, review aggregators, or vendor landing pages? What structure do they share?

Content brief generation

For the keyword [best CRM for plumbers], fetch the top-cited pages and tell me: (1) average page depth, (2) do they use listicles or comparison tables, (3) what entity types do they mention (brands, features, user types), (4) what content am I missing?

Competitive page analysis

Get the top 10 pages cited for [keyword]. Compare URLs from [competitor1.com] vs [competitor2.com] vs [mysite.com]. Which competitor's pages get cited most? What's their URL pattern (subdomain, path structure, slug style)?

Citation momentum tracking

Run top-pages for [keyword] every Monday for 8 weeks. Track whether our company's pages climb the citation ranking, which competitors drop, and whether new pages break into the top 10. Flag material changes.

▌ Real response

What you get back

Live response from POST /v1/ai/top-pages for 'best plumber Austin' across ChatGPT and Google AI.

response · application/json~4s · 5 credits
{
  "status": "success",
  "credits_used": 5,
  "data": {
    "keyword": "best plumber Austin",
    "location": "Austin, Texas",
    "ai_search_volume": 1200,
    "top_pages": [
      {
        "url": "https://yelp.com/search?find_desc=plumber&find_loc=Austin+TX",
        "domain": "yelp.com",
        "title": "Best Plumbers in Austin, TX - Yelp",
        "mentions": 32,
        "platforms": ["chat_gpt", "google"],
        "ai_search_volume": 1200
      },
      {
        "url": "https://homeadvisor.com/c.Plumbing.Austin.TX.html",
        "domain": "homeadvisor.com",
        "title": "Top-Rated Plumbers in Austin, TX",
        "mentions": 18,
        "platforms": ["chat_gpt", "google"],
        "ai_search_volume": 1200
      },
      {
        "url": "https://abc-plumbing.com/services/emergency-repair",
        "domain": "abc-plumbing.com",
        "title": "Emergency Plumbing Repair Austin | ABC Plumbing",
        "mentions": 12,
        "platforms": ["chat_gpt"],
        "ai_search_volume": 1200
      },
      {
        "url": "https://maps.google.com/maps?q=plumber+Austin+TX",
        "domain": "maps.google.com",
        "title": "Plumbers near Austin, TX",
        "mentions": 8,
        "platforms": ["google"],
        "ai_search_volume": 1200
      }
    ]
  }
}
▌ Returns

Granular page-level citation data for content teams

Exact cited URLs

Full URL, domain, and page title

Not just 'yelp.com is cited' — we capture the exact path, query string, and page title. You see the category page vs the review-aggregation page vs the business profile.

Per-page mention frequency

How many times each URL appears in AI responses

If a specific Yelp category page is cited 32 times and another is cited 2 times, you'll know the difference. Identify which page types and content structures get cited most.

Multi-platform breakdown

Which LLMs cite which pages

See that ChatGPT prefers the Yelp category page, while Google AI Overview prefers the Maps result. Different LLMs have different citation behavior — track each separately.

Page-level content analysis

Title, URL pattern, domain structure

Extract common patterns: Are cited pages listicles or reviews? Do they use dynamic query parameters? Are they at the domain root or in subfolders? Build a content template from the patterns.

▌ Built for

What AI-native operators ship with this

Content structure reverse engineering

Pull top-cited pages for 20 keywords in your category. Analyze the patterns: do listicles get cited more than deep guides? Are vendor pages or aggregator pages preferred? Build your content roadmap from LLM preferences, not search trends.

→ For content teams

Content brief generation for writers

Before writing a page, run this API on your target keyword. Show writers the exact pages LLMs cite, their structure, content depth, and entity mentions. Use that as the brief. Higher citation probability than guessing.

→ AI Content Ops

Competitive page benchmarking

See which of your competitor's pages rank highest in LLM citations. Analyze their content depth, structure, and topics. Use that intelligence to build pages that compete directly for the same citation slots.

→ For agencies

Citation momentum tracking

Schedule weekly or monthly checks on your target keywords. Track whether your pages climb or fall in the citation ranking. Know when a new competitor page breaks the top 10 and understand why.

→ Monitoring
▌ vs. the alternatives

Why not analyze competitor pages manually?

Checking which specific pages LLMs cite means executing hundreds of queries across ChatGPT, Claude, Gemini, and Perplexity, then parsing each response to extract URLs. Competitors charge $200–$2000/mo for this. We charge $0.025 per query, unlimited pages, unlimited keywords. Here's how the options stack up.

ApproachCost per queryURL-level granularityMulti-LLM trackingAgent-ready
Manual ChatGPT + Claude checking$0 but ~15 min labor per queryYou see the URLsWhatever you query manuallyNo
Profound (enterprise)$499–$2000/mo (~$16–65 per query)Yes, with page titles10+ platformsDashboard only
AthenaHQ$300–$1000/mo (~$10–33 per query)Domain-level mainlyChatGPT, Claude, Gemini, PerplexityDashboard + limited API
Otterly.ai$29–$99/mo (~$0.97–3.30 per query)Limited URL detail4 LLMs + Google AIReporting UI
Peec AI$99–$299/mo (~$3.30–10 per query)Some URL tracking4 platformsManual export
Local SEO Data AI Top Pages API$0.025 per callFull URL, title, mention countChatGPT, Claude, Gemini, PerplexityNative MCP, agent-first
▌ Connect in 60 seconds

Use it from your agent

Two integration surfaces: MCP for clients that speak MCP, REST API for everything else.

Direct MCP integration

Drop-in support in Claude Desktop, OpenClaw, Hermes Agent, and any MCP-aware client.

Add to your client's MCP config (e.g. claude_desktop_config.json):

{
  "mcpServers": {
    "localseodata": {
      "url": "https://mcp.localseodata.com",
      "headers": {
        "Authorization": "Bearer sk_live_..."
      }
    }
  }
}

REST API

For Perplexity Computer, ChatGPT Custom GPTs, custom agents, and any platform that calls REST endpoints directly.

Base URL:

api.localseodata.com

See the docs for endpoint reference and auth.

▌ Quickstart

Your first call in three lines

Core parameters: `keyword` (the search query to analyze) and optional `location` (e.g. 'Austin, TX', defaults to United States). You can specify which platforms to query — default is both ChatGPT and Google (Gemini/AI Overview). The `limit` parameter caps results per query (default 10, max 50). One call = 5 credits.

terminal · curl
POST /v1/ai/top-pages
curl -X POST https://api.localseodata.com/v1/ai/top-pages \
  -H "Authorization: Bearer sk_live_..." \
  -H "Content-Type: application/json" \
  -d '{
    "keyword": "best plumber Austin",
    "location": "Austin, Texas",
    "platforms": ["chat_gpt", "google"],
    "limit": 10
  }'
Full endpoint reference → · Get an API key →
▌ Pricing for this endpoint

$0.025 per top-pages query

Pay-as-you-go starts at $5. No monthly minimums. No per-seat licenses. No subscription required. Funds never expire.

Free tier
50
credits on signup (10 queries)
Starter · $5
200
credits, no expiration
Per-call cost
$0.025
per top-pages query
▌ FAQ

Common questions

What is the AI Top Pages API?+
A REST endpoint that returns the specific URLs (not just domains) that ChatGPT, Claude, Gemini, and Perplexity cite most for a given keyword. For each page, you get the full URL, domain, page title, citation count (how many times that URL appears in AI responses), which platforms cite it, and the AI search volume for that keyword. The endpoint is POST /v1/ai/top-pages; one call costs 5 credits (~$0.025). This is the data layer underneath content strategy, page-level competitive analysis, and citation pattern research.
How is AI Top Pages different from AI Top Sources?+
AI Top Sources (POST /v1/ai/top-sources) returns domain-level data: 'Yelp is cited 100 times, HomeAdvisor is cited 50 times.' AI Top Pages is the granular sibling: 'The Yelp category page is cited 32 times, the Yelp review-sort page is cited 18 times, HomeAdvisor's category page is cited 48 times.' Both are useful — Top Sources for broad competitive domain analysis, Top Pages for content teams reverse-engineering structure and page type preferences. Many teams query both: Top Sources for 'which domains dominate,' Top Pages for 'which specific pages should I model.'
Which LLMs do you track?+
ChatGPT (OpenAI), Claude (Anthropic), Gemini (Google), and Perplexity (Perplexity AI). You can also track Google AI Overviews via the Google platform filter. These are the major LLM surfaces driving real traffic in 2026. Each LLM has different training data and citation behavior — the same keyword may surface different pages prominently in ChatGPT vs Perplexity. You can query all four in one call or filter to specific platforms.
How do I use this for content strategy?+
Three workflows: (1) Content structure analysis: Pull top-cited pages for 20 keywords in your niche. Analyze patterns — are listicles cited more than deep guides? Do reviews outrank how-tos? Use those patterns to template your future content. (2) Content brief generation: Before writing a new page, run this API on your target keyword. Show writers the top-cited pages, their structure, and content depth. Write toward those patterns rather than guessing. (3) Competitive page benchmarking: See which competitor pages rank highest in LLM citations. Analyze their topics, entity mentions, and structure. Build pages that directly compete for the same citation slots.
Where does this URL data come from?+
We operate first-party collection infrastructure — our agents run your keywords directly against ChatGPT API, Claude API, Gemini API, Perplexity API, and Google AI Overviews. We execute the queries, capture the responses, parse them for cited URLs, extract page titles, and track mention frequency. We do not rely on cached or third-party data. This is why you see exact URLs and current mention counts. Data is fresh at call time, not hours or days old.
How fresh is the data?+
Each API call executes your keywords live against ChatGPT, Claude, Gemini, and Perplexity, so citations reflect current LLM training and behavior. LLM responses can vary between calls, so we execute multiple times per keyword to stabilize the signal and get accurate mention counts. Results are available within 4–8 seconds of the API call.
Can I track competitor pages?+
Yes. The API accepts any keyword — yours, your competitors', or generic market keywords. There's no ownership verification. This is what makes competitive page analysis work: pull top-cited pages for your competitor's branded keywords, see which specific pages get cited, and understand their content strategy from LLM behavior.
How does this compare to Profound, Topify, AthenaHQ, and Peec AI?+
Profound ($499–$2000/mo), Topify, AthenaHQ ($300–$1000/mo), and Peec AI ($99–$299/mo) all offer tools that track LLM page citations. Most are dashboard-focused, designed for humans to log in and read reports. Our API is designed for agents — your Claude prompt calls this endpoint, gets JSON, and acts on it without a dashboard. Pricing-wise: Profound costs $16–65 per query annualized; AthenaHQ costs $10–33; Peec costs $3.30–10; we charge $0.025 per call. If you're building agent workflows or analyzing 100+ keywords per month, API pricing eliminates the subscription trap. If you want a CEO dashboard, those tools are better suited.
Can my AI agent use this directly?+
Yes, and this is exactly what we built for. Two integration paths: MCP: add Local SEO Data to your claude_desktop_config.json and your Claude agent calls this endpoint from any prompt. REST: any agent that can make HTTPS calls (ChatGPT Custom GPTs, Perplexity Computer, custom Python/Node agents) hits the API directly with your Bearer token. The agent receives structured JSON, parses page patterns, and builds content strategies without human involvement.
What does it cost compared to competitors?+
We charge $0.025 per top-pages call (one keyword across selected LLMs, up to 50 pages returned). Profound costs $499–$2000/mo (~$16–65 per query). AthenaHQ costs $300–$1000/mo (~$10–33 per query). Peec AI costs $99–$299/mo. If you run 100 page queries per month, we cost $2.50 total; Profound costs $500+. If you run 10 queries per month, we cost $0.25; Profound still costs $500. Pay-per-call eliminates the monthly minimum that subscription tools impose.
What changed in 2026 that made URL-level citation tracking necessary?+
Two things: First, LLMs became mainstream search surfaces. ChatGPT, Claude, Gemini, and Perplexity now generate synthesized answers for billions of queries. When they cite your page vs a competitor's page, that affects real traffic. Second, content teams realized domain-level tracking (Yelp is cited a lot) is too broad — they need URL-level data to understand *which Yelp pages* LLMs prefer. Is it the category page? The review-sorted page? That difference determines your content template. URL-level citation tracking is a 2026 native category because content optimization for LLMs requires reverse-engineering page structure from the actual citations, and agents need API data to automate that analysis.
How does this relate to AI Top Sources and AI Visibility?+
Three complementary endpoints: AI Top Sources tells you which domains LLMs cite most — broad competitive intelligence. AI Visibility tells you how visible your domain is overall — a 0–100 score across platforms. AI Top Pages tells you which specific pages get cited most — granular content-strategy data. A complete AI search workflow uses all three: Visibility for monthly tracking, Top Sources for competitive landscape, Top Pages for content teams optimizing page structure.
▌ Related endpoints

Often used in the same agent prompt

POST /v1/ai/top-sources
AI Top Sources

Which domains LLMs cite most. The coarser sibling to this API.

POST /v1/ai/visibility
AI Visibility

Composite score: total mentions, impressions across LLMs.

POST /v1/ai/mentions
AI Mentions

Find where your brand appears in LLM responses with context.

POST /v1/ai/overview
AI Overview

Check if Google AI Overview cites your domain for queries.

Build content around the URLs LLMs actually cite.

50 free credits on signup. Your first top-pages query happens through your agent, not a spreadsheet.

Start FreeRead the docs
▌ MADE FOR THE NEW LOCAL SEO STACK