{ "openapi": "3.0.1", "info": { "title": "Text to JSON: Extract Structured Data from Any Document", "description": "Turn messy text, emails, HTML, PDFs and Word docs into clean JSON that matches your own schema. Invoices, receipts, forms, listings and emails. Free rule-based extraction, or bring your own LLM key. Built for AI agents and MCP.", "version": "1.0", "x-build-id": "JKZoACoPBndXA9KDd" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/birchwood-data~text-to-data/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-birchwood-data-text-to-data", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/birchwood-data~text-to-data/runs": { "post": { "operationId": "runs-sync-birchwood-data-text-to-data", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/birchwood-data~text-to-data/run-sync": { "post": { "operationId": "run-sync-birchwood-data-text-to-data", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "schema" ], "properties": { "text": { "title": "Text or HTML to extract from", "type": "string", "description": "Paste one document: an email, invoice, receipt, form, listing, chat message, HTML page source, etc. For several documents use 'Multiple texts' or 'Document URLs'." }, "schema": { "title": "Output schema (what JSON you want back)", "type": "object", "description": "Either a standard JSON Schema ({\"type\":\"object\",\"properties\":{...}}) or a simple shorthand: {\"name\": \"string\", \"total\": \"number\", \"date\": \"date\", \"email\": \"email\", \"paid\": \"boolean\", \"status\": \"open|closed\", \"tags\": [\"string\"], \"items\": [{\"description\": \"string\", \"qty\": \"integer\"}]}. Shorthand types: string, number, integer, boolean, date, datetime, email, url, phone, 'a|b|c' (enum). Nested objects and arrays of objects (tables / line items) are supported." }, "texts": { "title": "Multiple texts (batch)", "type": "array", "description": "Optional. A JSON array of documents: plain strings, or objects like {\"id\": \"msg-1\", \"text\": \"...\"} (the id is copied to the output). Each document becomes one output item." }, "urls": { "title": "Document URLs (PDF, DOCX, HTML, TXT, JSON, CSV)", "type": "array", "description": "Optional. Public links to documents. PDFs (with a text layer), Word .docx, web pages, text, JSON and CSV files are supported. Max 25 MB each. Scanned image-only PDFs need OCR first.", "items": { "type": "string" } }, "instructions": { "title": "Extra instructions (LLM mode)", "type": "string", "description": "Optional hints for the LLM, e.g. 'Amounts are in EUR', 'customer = the company being billed', 'dates are day-first'. Ignored by the rule-based extractor." }, "mode": { "title": "Extraction mode", "enum": [ "auto", "rules", "llm" ], "type": "string", "description": "auto = use your LLM key if you provide one, otherwise the free rule-based extractor. rules = always rule-based (fast, deterministic, no AI cost). llm = always use your LLM key.", "default": "auto" }, "llmProvider": { "title": "LLM provider", "enum": [ "openai", "anthropic", "gemini", "openrouter", "groq", "mistral", "deepseek", "openai-compatible" ], "type": "string", "description": "Which provider your API key is for. Your key is billed by that provider directly; this Actor never adds a markup.", "default": "openai" }, "llmApiKey": { "title": "Your LLM API key", "type": "string", "description": "Optional. Your own API key for the provider above. Stored encrypted by Apify, used only for this run, never logged or saved to the output." }, "llmModel": { "title": "Model", "type": "string", "description": "Optional model ID. Defaults: OpenAI gpt-6-luna, Anthropic claude-haiku-4-5, Gemini gemini-3.1-flash-lite, OpenRouter openai/gpt-6-luna, Groq llama-3.3-70b-versatile, Mistral mistral-small-latest, DeepSeek deepseek-chat. Required for 'openai-compatible'." }, "llmBaseUrl": { "title": "Custom base URL", "type": "string", "description": "Optional. For 'openai-compatible' (e.g. https://your-host/v1) or to route a provider through a proxy/gateway." }, "fallbackToRules": { "title": "Fall back to rule-based extraction if the LLM fails", "type": "boolean", "description": "If your LLM call errors (bad key, quota, timeout), still return a rule-based result instead of failing that document. The LLM error is reported in 'llmError'.", "default": true }, "includeSourceText": { "title": "Include the cleaned source text in the output", "type": "boolean", "description": "Adds 'sourceText' (the plain text we extracted from the document) to each output item. Handy for debugging or RAG.", "default": false }, "maxCharsPerDocument": { "title": "Max characters per document", "minimum": 1000, "maximum": 1000000, "type": "integer", "description": "Longer documents are truncated to this many characters (the output says 'truncated': true).", "default": 120000 }, "maxConcurrency": { "title": "Documents processed in parallel", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many documents to fetch/extract at the same time.", "default": 3 } } }, "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 } } } } } } } } } }