{ "openapi": "3.0.1", "info": { "title": "AI Schema Web Extractor: BYOK + Browser Fallback", "description": "Extract schema-validated JSON from URLs with your own LLM key. Starts on fast HTTP and renders JavaScript only when the page needs it, with source evidence for the fields.", "version": "0.1", "x-build-id": "ulFxICH4PewmnynJd" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/automa-flow~ai-schema-web-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-automa-flow-ai-schema-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/automa-flow~ai-schema-web-extractor/runs": { "post": { "operationId": "runs-sync-automa-flow-ai-schema-web-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/automa-flow~ai-schema-web-extractor/run-sync": { "post": { "operationId": "run-sync-automa-flow-ai-schema-web-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "schema", "llmProvider" ], "properties": { "urls": { "title": "URLs", "minItems": 1, "maxItems": 500, "type": "array", "description": "1 to 500 public http or https pages you are allowed to process. Exact normalized duplicates are dropped. Localhost, private networks and file downloads are reported per URL.", "items": { "type": "string", "minLength": 1, "maxLength": 2048, "pattern": "^https?://\\S+$" } }, "schema": { "title": "JSON Schema", "type": "object", "description": "JSON Schema for one object, or an array of objects. Draft 2020-12 and draft-07 only. Local $ref such as #/$defs/Price (Pydantic or Zod export) is inlined. Remote or recursive $ref and conditional keywords are rejected before any page is fetched." }, "instructions": { "title": "Instructions", "maxLength": 2000, "type": "string", "description": "Optional note for the model, such as which product on the page to extract. Webpage text is never treated as instructions.", "default": "" }, "llmProvider": { "title": "Model provider", "enum": [ "openai", "anthropic" ], "type": "string", "description": "Bring your own key. openai and anthropic are the supported providers. An Anthropic key (sk-ant-...) or a Claude model uses anthropic, and an OpenAI key uses openai, whatever this field says. The Actor does not sell model tokens.", "default": "openai" }, "apiKey": { "title": "API key", "type": "string", "description": "Your OpenAI or Anthropic key. Required when test mode is off, otherwise the run stops at startup with API_KEY_REQUIRED. Leave empty in test mode. The key is not stored, logged or written to the dataset." }, "model": { "title": "Model", "pattern": "^(gpt-5\\.6-terra|gpt-5\\.6-luna|gpt-5\\.6-sol|claude-haiku-4-5|claude-sonnet-5)$", "maxLength": 64, "type": "string", "description": "Optional allowlisted model id. OpenAI defaults to gpt-5.6-terra. Anthropic defaults to claude-haiku-4-5. Arbitrary endpoint URLs are rejected." }, "renderingMode": { "title": "Rendering", "enum": [ "HTTP_ONLY", "AUTO", "BROWSER" ], "type": "string", "description": "AUTO fetches HTTP first and opens a browser only when the static page is too thin. HTTP_ONLY never renders. BROWSER renders every URL once, still without login or CAPTCHA bypass. BROWSER stops before fetch unless the charge limit covers at least $0.006.", "default": "AUTO" }, "includeEvidence": { "title": "Include evidence", "type": "boolean", "description": "Ask the model for a source quote per extracted field and check that the quote appears in the page text. This is a presence check, not a confidence score.", "default": true }, "maxInputChars": { "title": "Max input characters", "minimum": 2000, "maximum": 80000, "type": "integer", "description": "Maximum characters of cleaned page text sent to the model. Structured blocks are included first. The row records how many characters were sent.", "default": 40000 }, "testMode": { "title": "Test mode", "type": "boolean", "description": "On, the Actor returns a labeled non-live fixture for your schema and does not fetch pages or call a model. Turn this off for a live extraction.", "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 } } } } } } } } } }