# GEO Citation Tracker - URL & Source Citations in AI Answers (`dltik/geo-citation-tracker`) Actor Track how often AI models cite your domain as a source. Detect URL citations, source mentions, and reference patterns across ChatGPT, Claude, and Gemini. Higher per-call value than mention-only tracking. Pairs with GEO Visibility Score. - **URL**: https://apify.com/dltik/geo-citation-tracker.md - **Developed by:** [dltik](https://apify.com/dltik) (community) - **Categories:** AI, Marketing, Developer tools - **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, NaN bookmarks - **User rating**: No ratings yet ## Pricing from $0.00005 / actor start This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Actors are written with capital "A". ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README ## GEO Citation Tracker — URL & Source Citations in AI Answers **GEO Citation Tracker** detects when ChatGPT, Claude, and Gemini cite your domain as a source. Goes beyond mention-tracking: catches explicit URL citations (`https://yourdomain.com/page`), bare domain references (`yourdomain.com`), and brand-as-source phrasing ("according to YourBrand", "per YourBrand's docs"). Citations carry more authority weight than mentions — this is the upstream signal you need for AEO. Stop wondering whether AI is sourcing your content. Get a clear citation score per LLM, top-cited URLs, and a strength tier (strong / medium / weak / none) for every response. > ⭐ **Found this useful?** Click the **Bookmark** button at the top of [this page](https://apify.com/dltik/geo-citation-tracker) — it helps the actor stay visible to others who need it. Takes 1 click. No signup beyond your existing Apify account. --- ### What can GEO Citation Tracker detect? - 🔗 **URL citations** — explicit `https://yourdomain.com/...` references in AI answers - 🏷️ **Bare domain mentions** — `yourdomain.com` without protocol - 📜 **Brand-as-source attributions** — "according to YourBrand", "per YourBrand's docs", "YourBrand reports..." - 💪 **Citation strength tier** — strong (URL) / medium (≥2 domain or source-phrase) / weak / none - 📊 **Citation rate** — % of responses citing your domain at all - 🥇 **Strong citation rate** — % of responses with a real URL citation - 🤖 **Per-LLM breakdown** — which AI cites you most? Which never does? - 🌐 **Top cited URLs** — exact pages AI is sourcing --- ### What data does GEO Citation Tracker extract? | Field | Description | |-------|-------------| | `prompt` | The query sent to the LLM | | `model` | The OpenRouter model (e.g. `openai/gpt-4o-mini`) | | `response_text` | First 1500 chars of the LLM's answer | | `has_citation` | Whether your domain appears in any form | | `url_citations` | Explicit URLs from your domain | | `domain_mentions` | Count of bare domain references | | `brand_source_mentions` | Count of "according to BRAND" patterns | | `citation_strength` | `strong` / `medium` / `weak` / `none` | | `citation_metrics.score` | 0-100 weighted score across all responses | | `top_cited_urls` | Top 20 unique URLs cited, with frequency | --- ### How to track AI citations of your domain 1. **[Create a free Apify account](https://apify.com/sign-up)** 2. **Open [GEO Citation Tracker](https://apify.com/dltik/geo-citation-tracker)** in Apify Store 3. **Enter your domain** (e.g. `notion.so`) and brand name (e.g. `Notion`) 4. **Provide citation-prone prompts** — questions that ask for sources/references 5. **Click Start** — runs prompts × LLMs, ~30–60 seconds 6. **Download the citation report** (JSON / CSV / Excel) **Pro tip**: prompts that explicitly ask for sources ("Cite sources", "Include references", "What does the documentation say?") trigger far more citations than open-ended questions. --- ### How much does GEO citation tracking cost? **$0.07 per citation analyzed** via Apify Pay-Per-Event. Includes the OpenRouter API call cost. | Run | Prompts × LLMs | Total events | Cost | |-----|----------------|--------------|------| | Quick test (4 prompts × 1 LLM) | 4 | 4 | ~$0.28 | | Standard (4 prompts × 3 LLMs) | 12 | 12 | ~$0.84 | | Deep audit (8 prompts × 3 LLMs) | 24 | 24 | ~$1.68 | A full citation audit costs ~$0.84 — vs $300+ for a manual GEO/AEO consultant. --- ### Input | Parameter | Type | Required | Default | Description | |-----------|------|----------|---------|-------------| | `domain` | string | ✅ | — | Bare domain (e.g. `notion.so`) | | `brand` | string | ❌ | derived | Brand name for fuzzy source-attribution detection | | `prompts` | array | ❌ | 4 defaults | Citation-prone prompts (use `{brand}` and `{domain}` placeholders) | | `llms` | array | ❌ | 3 models | OpenRouter model IDs to query | | `limit` | integer | ❌ | `8` | Max prompts per run | | `openrouterApiKey` | string | ❌ | env var | Override the default OpenRouter key | --- ### Why citations matter more than mentions A mention says: AI knows you exist. A citation says: AI considers you authoritative. When AI cites your URL or attributes a claim to "YourBrand's docs", it's signaling that **your content is the source of truth** for that query. This translates to: - Higher click-through from AI answers (when grounded responses link out) - Better positioning in subsequent fine-tuning rounds (AI labs scrape for high-quality cited domains) - Stronger E-E-A-T signal when humans verify AI output Track citations weekly. If your strong-citation rate is rising, your AEO is working. --- ### Related GEO actors This actor pairs with the rest of the GEO suite: - **[GEO Prompt Bank](https://apify.com/dltik/geo-prompt-bank)** — pre-built buying-intent prompts per industry - **[GEO Visibility Score](https://apify.com/dltik/geo-visibility-score)** — measure overall brand mention rate across LLMs - **[GEO Brand Sentiment](https://apify.com/dltik/geo-brand-sentiment)** — analyze how AI describes your brand - **[GEO Site Audit](https://apify.com/dltik/geo-site-audit)** — audit your website for AI readability - **[GEO Prompt Research](https://apify.com/dltik/geo-prompt-research)** — discover net-new prompts for your niche --- > ⭐ **Bookmark this actor** at the top of [its Apify Store page](https://apify.com/dltik/geo-citation-tracker) — keeps it visible for the next person who needs it. # Actor input Schema ## `domain` (type: `string`): Domain to track citations for (e.g. 'notion.so', 'stripe.com'). Strip protocol — just the bare domain. ## `brand` (type: `string`): Brand name for fuzzy matching when AI cites without a URL (e.g. 'According to Notion's docs'). Falls back to domain root. ## `prompts` (type: `array`): Citation-prone prompts. Best results: prompts that ask for sources/references/data. Use {brand} and {domain} placeholders. ## `llms` (type: `array`): OpenRouter models to query. Default: 3 models with web/search-enabled variants when supported. ## `limit` (type: `integer`): Cap total prompts. Each prompt × LLM = 1 charged event. ## `openrouterApiKey` (type: `string`): Override the default OpenRouter key. Get one at openrouter.ai/keys. ## Actor input object example ```json { "domain": "notion.so", "brand": "Notion", "prompts": [ "What's the best note-taking app in 2026? Include sources.", "How does {brand} handle data privacy? Cite sources.", "What features does {brand} have? Reference official docs.", "Who uses {brand} and why? Provide source links." ], "llms": [ "google/gemini-2.0-flash-001", "openai/gpt-4o-mini", "anthropic/claude-haiku-4.5" ], "limit": 8 } ```` # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "domain": "notion.so", "brand": "Notion", "prompts": [ "What's the best note-taking app in 2026? Include sources.", "How does {brand} handle data privacy? Cite sources.", "What features does {brand} have? Reference official docs.", "Who uses {brand} and why? Provide source links." ] }; // Run the Actor and wait for it to finish const run = await client.actor("dltik/geo-citation-tracker").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "domain": "notion.so", "brand": "Notion", "prompts": [ "What's the best note-taking app in 2026? Include sources.", "How does {brand} handle data privacy? Cite sources.", "What features does {brand} have? Reference official docs.", "Who uses {brand} and why? Provide source links.", ], } # Run the Actor and wait for it to finish run = client.actor("dltik/geo-citation-tracker").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{ "domain": "notion.so", "brand": "Notion", "prompts": [ "What'\''s the best note-taking app in 2026? Include sources.", "How does {brand} handle data privacy? Cite sources.", "What features does {brand} have? Reference official docs.", "Who uses {brand} and why? Provide source links." ] }' | apify call dltik/geo-citation-tracker --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=dltik/geo-citation-tracker", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "GEO Citation Tracker - URL & Source Citations in AI Answers", "description": "Track how often AI models cite your domain as a source. Detect URL citations, source mentions, and reference patterns across ChatGPT, Claude, and Gemini. Higher per-call value than mention-only tracking. Pairs with GEO Visibility Score.", "version": "1.0", "x-build-id": "40w7QjZtfeqebgIFZ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/dltik~geo-citation-tracker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-dltik-geo-citation-tracker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/dltik~geo-citation-tracker/runs": { "post": { "operationId": "runs-sync-dltik-geo-citation-tracker", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/dltik~geo-citation-tracker/run-sync": { "post": { "operationId": "run-sync-dltik-geo-citation-tracker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "domain" ], "properties": { "domain": { "title": "Your domain", "type": "string", "description": "Domain to track citations for (e.g. 'notion.so', 'stripe.com'). Strip protocol — just the bare domain." }, "brand": { "title": "Your brand name (optional)", "type": "string", "description": "Brand name for fuzzy matching when AI cites without a URL (e.g. 'According to Notion's docs'). Falls back to domain root." }, "prompts": { "title": "Prompts to test", "type": "array", "description": "Citation-prone prompts. Best results: prompts that ask for sources/references/data. Use {brand} and {domain} placeholders.", "items": { "type": "string" } }, "llms": { "title": "LLMs to query", "type": "array", "description": "OpenRouter models to query. Default: 3 models with web/search-enabled variants when supported.", "default": [ "google/gemini-2.0-flash-001", "openai/gpt-4o-mini", "anthropic/claude-haiku-4.5" ] }, "limit": { "title": "Max prompts per run", "minimum": 1, "maximum": 50, "type": "integer", "description": "Cap total prompts. Each prompt × LLM = 1 charged event.", "default": 8 }, "openrouterApiKey": { "title": "Your OpenRouter API key (optional)", "type": "string", "description": "Override the default OpenRouter key. Get one at openrouter.ai/keys." } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } } ```