{ "openapi": "3.0.1", "info": { "title": "CMS Hospital Price Transparency Scraper", "description": "Extract hospital standard charges from CMS-mandated machine-readable files (MRF). Parses CMS JSON (v1/v2/v3) and CSV (v2/v3, tall and wide) files into rows by billing code and payer/plan. Reads hospital identity from CMS enrollment data. Filter by state, CCN, code type, billing code, or payer.", "version": "0.1", "x-build-id": "WOG8UokPZMAdz7w6b" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/jungle_synthesizer~cms-hospital-price-transparency-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-jungle_synthesizer-cms-hospital-price-transparency-scraper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/jungle_synthesizer~cms-hospital-price-transparency-scraper/runs": { "post": { "operationId": "runs-sync-jungle_synthesizer-cms-hospital-price-transparency-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/jungle_synthesizer~cms-hospital-price-transparency-scraper/run-sync": { "post": { "operationId": "run-sync-jungle_synthesizer-cms-hospital-price-transparency-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "sp_intended_usage", "sp_improvement_suggestions" ], "properties": { "sp_intended_usage": { "title": "What is the intended usage of this data?", "minLength": 1, "type": "string", "description": "What will this data feed? E.g. lead lists, KYB checks, price tracking." }, "sp_improvement_suggestions": { "title": "How can we improve this crawler for you?", "minLength": 1, "type": "string", "description": "Provide any feedback or suggestions for improvements." }, "sp_contact": { "title": "Contact email (optional)", "minLength": 1, "type": "string", "description": "We'll personally help with your use case. No spam." }, "mode": { "title": "Mode", "enum": [ "hospital_list", "mrf_parse", "discover_and_parse" ], "type": "string", "description": "hospital_list returns hospital enrollment data from CMS. mrf_parse fetches and parses a single MRF URL you supply. discover_and_parse finds each hospital's MRF through its cms-hpt.txt and returns one discovery status record per hospital plus its charge rows (maxItems counts both).", "default": "mrf_parse" }, "mrfUrl": { "title": "MRF URL", "type": "string", "description": "Machine-readable file URL to fetch and parse. Required for mrf_parse mode. Supports JSON (CMS v1/v2/v3 schema) and CSV (CMS v2/v3 tall or wide template); CSV files are streamed, so size is not a concern." }, "hospitalDomain": { "title": "Hospital Website (discover_and_parse)", "type": "string", "description": "Website host of the hospital (e.g. www.cmhc.org) to look up cms-hpt.txt on, skipping the automatic website lookup. Use with Hospital CCN Filter. Leave blank to look websites up automatically." }, "maxMrfSizeMb": { "title": "Max MRF Size in MB (discover_and_parse)", "type": "integer", "description": "Discovered JSON MRF files larger than this are reported in the discovery record but not downloaded (JSON is parsed whole, so raise it together with the run memory). CSV files are streamed and have no size limit.", "default": 64 }, "stateFilter": { "title": "State Filter", "type": "string", "description": "Two-letter state code (e.g. CA, TX). Filters hospital list results. Leave blank for all states." }, "hospitalCcn": { "title": "Hospital CCN Filter", "type": "string", "description": "CMS Certification Number to filter to a single hospital. Leave blank for all." }, "billingCodeType": { "title": "Billing Code Type Filter", "enum": [ "", "CPT", "HCPCS", "MS-DRG", "APR-DRG", "RC", "NDC", "Internal" ], "type": "string", "description": "Filter charge rows by billing code system. Leave blank for all." }, "billingCode": { "title": "Billing Code", "type": "string", "description": "Specific billing code to filter (e.g. 70551 for CPT Brain MRI). Leave blank for all." }, "payerFilter": { "title": "Payer Name Contains", "type": "string", "description": "Filter charge rows by payer name substring (case-insensitive). Leave blank for all." }, "maxItems": { "title": "Max Items", "type": "integer", "description": "Maximum charge rows or hospital records to return. 0 = unlimited.", "default": 15 } } }, "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 } } } } } } } } } }