{ "openapi": "3.0.1", "info": { "title": "LLM Web Data Extractor for OpenAI, Anthropic, Gemini Keys", "description": "Turn public web pages into structured JSON with your own OpenAI, Anthropic or Gemini API key. List the fields you want or paste a JSON Schema; get one clean row per page with the tokens your key used. No login, no scraping code.", "version": "0.1", "x-build-id": "IUtoUOux3yGdPy6r4" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/cliqtomedia~llm-web-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-cliqtomedia-llm-web-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/cliqtomedia~llm-web-extractor/runs": { "post": { "operationId": "runs-sync-cliqtomedia-llm-web-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/cliqtomedia~llm-web-extractor/run-sync": { "post": { "operationId": "run-sync-cliqtomedia-llm-web-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "urls" ], "properties": { "urls": { "title": "Page URLs", "type": "array", "description": "Public pages to read (up to 300 per run; 300 pages take about 18 minutes on a free Gemini key, so raise the run timeout). One model call per page. Pages behind a login or paywall, private and internal addresses are not read. Pages that render only with JavaScript are reported as JS_REQUIRED without a model call.", "items": { "type": "string" } }, "fields": { "title": "Fields to extract", "type": "array", "description": "Field name on the left, a short description for the model on the right. Add a type after a colon: price:number, count:integer, in_stock:boolean, tags:array (text by default). Missing values come back as null. Ignored when a JSON Schema is given.", "items": { "type": "object", "required": [ "key", "value" ], "properties": { "key": { "type": "string", "title": "Key" }, "value": { "type": "string", "title": "Value" } } } }, "mode": { "title": "One record or a list per page", "enum": [ "single", "list" ], "type": "string", "description": "One record: the fields describe the page itself (an article, a product). List: the page holds many records (plans, products, people) and you get them all in data.items.", "default": "single" }, "provider": { "title": "LLM provider", "enum": [ "gemini", "openai", "anthropic" ], "type": "string", "description": "Whose API your key belongs to. Gemini has a free tier in Google AI Studio. Anthropic support is built to the public API docs but not yet tested with a live key.", "default": "gemini" }, "apiKey": { "title": "Your API key", "type": "string", "description": "Your own key for the provider above. Required: without it the run stops at once with a hint and nothing is charged for extraction. The provider bills the tokens to this key. The key is stored encrypted, used for this run only and never written to logs or results. Gemini: aistudio.google.com/apikey · OpenAI: platform.openai.com/api-keys · Anthropic: console.anthropic.com/settings/keys" }, "model": { "title": "Model", "type": "string", "description": "Model id from your provider. Empty = a fast, low-cost default: gemini-flash-lite-latest, gpt-5.4-mini or claude-haiku-5-5. Reasoning models are slower and use more tokens." }, "jsonSchema": { "title": "JSON Schema (advanced)", "type": "object", "description": "Instead of fields, paste a JSON Schema whose root is an object with properties. It replaces the fields above. OpenAI uses strict mode only when every object lists all its properties as required and sets additionalProperties to false." }, "instructions": { "title": "Extra instructions", "type": "string", "description": "Optional hints for the model, up to 4000 characters. Example: give prices as numbers in USD; skip enterprise plans." }, "maxPageChars": { "title": "Max page characters sent", "minimum": 2000, "maximum": 200000, "type": "integer", "description": "Page text longer than this is cut before it is sent, to cap the tokens your key pays for (about 4 characters per token). The row says when a page was cut.", "default": 40000 }, "maxConcurrency": { "title": "Pages at the same time", "minimum": 1, "maximum": 10, "type": "integer", "description": "Parallel pages. Lower it if your key has a small rate limit (for example a free tier).", "default": 3 }, "keepBoilerplate": { "title": "Keep navigation and footer", "type": "boolean", "description": "Send the whole page, including menus, headers and footers. Off by default to save tokens.", "default": false } } }, "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 } } } } } } } } } }