Small Sitemap Inventory
Pricing
$1.00 / 1,000 unique sitemap urls
Go to Apify Store
Small Sitemap Inventory
Build a bounded same-host URL inventory from small public HTTPS sitemaps with explicit completeness and source receipts.
Small Sitemap Inventory
Pricing
$1.00 / 1,000 unique sitemap urls
Build a bounded same-host URL inventory from small public HTTPS sitemaps with explicit completeness and source receipts.
You can access the Small Sitemap Inventory programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.1", "x-build-id": "5gaiqag4R0F1VtmAN" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sapph1re~small-sitemap-inventory/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sapph1re-small-sitemap-inventory", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/sapph1re~small-sitemap-inventory/runs": { "post": { "operationId": "runs-sync-sapph1re-small-sitemap-inventory", "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/sapph1re~small-sitemap-inventory/run-sync": { "post": { "operationId": "run-sync-sapph1re-small-sitemap-inventory", "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": "Sitemap URLs", "minItems": 1, "maxItems": 10, "type": "array", "description": "One to ten public HTTPS sitemap or sitemap-index URLs. Credentials, fragments, sensitive query keys, cross-host declarations, and non-public addresses are rejected.", "default": [ { "url": "https://docs.apify.com/sitemap_base.xml" } ], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxDepth": { "title": "Maximum index depth", "minimum": 0, "maximum": 3, "type": "integer", "description": "Maximum child sitemap depth below each input sitemap.", "default": 2 }, "maxSources": { "title": "Maximum fetched sitemap files", "minimum": 1, "maximum": 50, "type": "integer", "description": "Hard ceiling on sitemap files attempted after URL validation.", "default": 20 }, "maxRequests": { "title": "Maximum HTTP requests", "minimum": 1, "maximum": 100, "type": "integer", "description": "Hard ceiling including each redirect hop. There are no retries.", "default": 40 }, "maxQueuedSources": { "title": "Maximum accepted sitemap sources", "minimum": 1, "maximum": 100, "type": "integer", "description": "Bounds queued and deduplicated source metadata. Must be at least maxSources.", "default": 50 }, "maxUrls": { "title": "Maximum unique URL rows", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Hard default-dataset row ceiling before billing limits are applied.", "default": 100 }, "maxDeclarations": { "title": "Maximum XML declarations examined", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Bounds direct sitemap or URL entries examined across all source files.", "default": 5000 }, "maxProvenancePerUrl": { "title": "URL provenance detail limit", "minimum": 1, "maximum": 10, "type": "integer", "description": "Maximum retained source and declaration details for one unique URL. Truncation makes completeness false.", "default": 5 }, "maxProvenancePerSource": { "title": "Source-parent detail limit", "minimum": 1, "maximum": 10, "type": "integer", "description": "Maximum retained parents or input positions for one deduplicated sitemap source.", "default": 5 }, "maxDiagnosticsPerSource": { "title": "Diagnostic sample limit", "minimum": 1, "maximum": 20, "type": "integer", "description": "Maximum retained rejected-declaration samples per source; aggregate counters remain bounded separately.", "default": 10 }, "maxOutputBytes": { "title": "Inventory byte limit", "minimum": 16384, "maximum": 8388608, "type": "integer", "description": "Maximum compact JSON bytes represented by dataset-eligible inventory rows.", "default": 2097152 }, "timeoutSeconds": { "title": "Per-source end-to-end timeout", "minimum": 1, "maximum": 10, "type": "integer", "description": "Deadline shared by DNS resolution, redirect hops, connection, and body reads for one sitemap source.", "default": 10 }, "maxRedirects": { "title": "Maximum redirects per source", "minimum": 0, "maximum": 3, "type": "integer", "description": "Only redirects to the exact root host are accepted and revalidated.", "default": 2 } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Small Sitemap Inventory from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: