{ "openapi": "3.0.1", "info": { "title": "AI Bot Analytics & AI Crawler Checker (GPTBot, llms.txt)", "description": "Google Analytics for AI agents: see which AI bots (GPTBot, ClaudeBot, PerplexityBot, ChatGPT-User...) hit your site and what pages they want, from your access logs, with fake-bot detection. Plus an AI-readiness audit: robots.txt per AI bot, firewall blocks, llms.txt, sitemap, schema, score.", "version": "0.1", "x-build-id": "ZujzCnzEMhdxabKkg" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/api-co~ai-bot-analytics/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-api-co-ai-bot-analytics", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/api-co~ai-bot-analytics/runs": { "post": { "operationId": "runs-sync-api-co-ai-bot-analytics", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/api-co~ai-bot-analytics/run-sync": { "post": { "operationId": "run-sync-api-co-ai-bot-analytics", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "startUrls": { "title": "Websites to audit", "type": "array", "description": "Domains or page URLs, e.g. 'example.com' or 'https://example.com/pricing'. Each gets an AI-readiness audit: robots.txt rules for 37 AI and search bots, a live firewall test, llms.txt, sitemap, structured data and text visible without JavaScript. Leave empty (and add no logs) to audit two example sites.", "items": { "type": "string" } }, "probeBotAccess": { "title": "Live-test whether your firewall/CDN blocks AI bots", "type": "boolean", "description": "Requests each page with the GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot and PerplexityBot user agents and compares the answer with a normal browser. Catches Cloudflare 'Block AI bots', WAF rules and 403s that robots.txt does not show.", "default": true }, "logUrls": { "title": "Access log file URLs", "type": "array", "description": "Direct links to server/CDN access logs (plain or .gz): a signed S3/GCS/R2 URL, a Dropbox/Drive direct link, or an Apify key-value store record URL. Formats are detected automatically: Apache/Nginx combined or common, JSON lines (Cloudflare Logpush, Vercel, Caddy, Fastly, Netlify and generic keys) and W3C logs with a #Fields: header (CloudFront, IIS).", "items": { "type": "string" } }, "logText": { "title": "Or paste log lines", "type": "string", "description": "Paste access-log lines directly (good for a quick look; use log URLs for big files)." }, "verifyBotIps": { "title": "Verify bots against official IP lists", "type": "boolean", "description": "Checks each hit against the IP ranges published by OpenAI, Perplexity, Google, Bing, Apple, Common Crawl, DuckDuckGo and Mistral, and counts hits from other IPs as suspected fake bots.", "default": true }, "includeSearchEngines": { "title": "Include Googlebot and Bingbot rows", "type": "boolean", "description": "Add Googlebot and Bingbot to the per-bot report for comparison (they are never counted as AI bot traffic).", "default": true }, "maxPathRows": { "title": "Top pages to report", "minimum": 0, "maximum": 1000, "type": "integer", "description": "How many 'most-requested by AI bots' page rows to output.", "default": 25 }, "maxLogLines": { "title": "Max log lines", "minimum": 1, "type": "integer", "description": "Safety limit on lines read across all log files.", "default": 20000000 }, "maxConcurrency": { "title": "Sites audited in parallel", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many websites to audit at the same time.", "default": 4 }, "maxItems": { "title": "Max results", "minimum": 1, "type": "integer", "description": "Stop after this many result rows (site audits + report rows). You are only charged per row.", "default": 1000 } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }