{ "openapi": "3.0.1", "info": { "title": "AI List Extractor for Any Website", "description": "Describe a list in plain words and give web addresses. Your own OpenAI, Anthropic, Gemini, or Groq key reads each page and returns one row per item, with a check that flags values not found on the page. No selectors and no per site code.", "version": "0.1", "x-build-id": "mxVitjtF5fwqTeQM8" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/mambalabs~ai-list-extractor-any-website/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-mambalabs-ai-list-extractor-any-website", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/mambalabs~ai-list-extractor-any-website/runs": { "post": { "operationId": "runs-sync-mambalabs-ai-list-extractor-any-website", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/mambalabs~ai-list-extractor-any-website/run-sync": { "post": { "operationId": "run-sync-mambalabs-ai-list-extractor-any-website", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "start_urls": { "title": "Web addresses", "type": "array", "description": "Public list pages that answer without a login, for example a careers page or a category page. A page that needs JavaScript or refuses plain requests returns a free row.", "items": { "type": "string" } }, "what_to_extract": { "title": "What one item is", "type": "string", "description": "Plain words, for example: every job: title, company, city, link. Needed when a key is given." }, "fields": { "title": "Item keys (optional)", "type": "array", "description": "Exact keys each item must carry, for the same columns on every page. Empty lets the model choose. In Clay, wrap a column in a one item list.", "items": { "type": "string" } }, "provider": { "title": "LLM provider", "type": "string", "description": "Whose API reads the page, on your key: openai (default), anthropic, gemini, or groq.", "default": "openai" }, "api_key": { "title": "Your provider API key", "type": "string", "description": "Your own key. It goes only to the provider you picked and is never stored, logged, or sent to the model. With no key the actor reads up to 3 addresses for free and sends nothing to a model." }, "model": { "title": "Model (optional)", "type": "string", "description": "Your provider's model name. Defaults: openai gpt-4o-mini, anthropic claude-haiku-4-5-20251001, gemini gemini-2.5-flash, groq llama-3.3-70b-versatile." }, "max_pages_per_url": { "title": "Pages per address", "type": "string", "description": "How many pages to read from each address by following next page links. Default 3, at most 100. Each page your model answers is charged.", "default": "3" }, "max_items": { "title": "Most items in a run", "type": "string", "description": "The run stops after this many items. Default 1000.", "default": "1000" }, "max_chars_per_page": { "title": "Most characters sent per page", "type": "string", "description": "Page text past this length is not sent, which limits your provider bill. Default 40000. The row says when text was cut.", "default": "40000" }, "obey_robots": { "title": "Obey robots.txt", "type": "string", "description": "yes (default) or no. A disallowed page returns a free row.", "default": "yes" }, "max_charge_usd": { "title": "Maximum charge in USD (optional)", "type": "string", "description": "Stops before a page would pass this figure, before your model is called. This limits this actor's charges, not your provider's bill." }, "source_tag": { "title": "Source tag", "type": "string", "description": "Internal attribution tag. Leave empty." } } }, "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 } } } } } } } } } }