{ "openapi": "3.0.1", "info": { "title": "URL to Markdown for AI Agents: Clean LLM Context", "description": "Clean main-content Markdown from up to 200 URLs a run, for AI agents and RAG: title, token estimate, optional chunks. $2.00 per 1,000 pages converted, failures free. Plain HTTP, no browser: a JavaScript-rendered page returns needs_browser, a PDF not_html. No crawl: it reads only the URLs you give.", "version": "1.0", "x-build-id": "umxRLocf6fmrRob4B" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/edgef-4~url-to-markdown-for-ai-agents/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-edgef-4-url-to-markdown-for-ai-agents", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/edgef-4~url-to-markdown-for-ai-agents/runs": { "post": { "operationId": "runs-sync-edgef-4-url-to-markdown-for-ai-agents", "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/edgef-4~url-to-markdown-for-ai-agents/run-sync": { "post": { "operationId": "run-sync-edgef-4-url-to-markdown-for-ai-agents", "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": "URLs", "minItems": 1, "maxItems": 200, "type": "array", "description": "Required. Page URLs, one per line, such as https://example.com/article (a bare domain like example.com gets https://). At most 200 per run; duplicates (also spellings that differ only in host case, default port or fragment) are processed once. Objects of the form {\"url\": \"...\"} are also accepted.", "items": { "type": "string" } }, "includeLinks": { "title": "Include links", "type": "boolean", "description": "Default true: links stay as [text](absolute URL). False keeps only the link text, which saves tokens. Images are always kept as ![alt text](absolute URL).", "default": true }, "maxChars": { "title": "Max characters per page", "minimum": 500, "maximum": 2000000, "type": "integer", "description": "Optional cap on the Markdown length per page, for example 20000 (at least 500). The text is cut at the last heading that fits in the second half of the limit (else at the last paragraph break), and the item gets truncated=true. Empty: no limit." }, "chunk": { "title": "Chunk mode", "type": "boolean", "description": "Default false. True adds a chunks array: the Markdown split into pieces of 800 to 1,200 tokens (the last one may be smaller) along heading boundaries, each with its heading path. Ready for embedding or RAG.", "default": false }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Pages fetched in parallel across all domains: default 5, from 1 to 20. Requests to the same domain are always spaced out (see minDelayPerDomainSecs).", "default": 5 }, "minDelayPerDomainSecs": { "title": "Minimum delay per domain", "minimum": 0.2, "maximum": 30, "type": "number", "description": "Minimum seconds between two requests to the same domain: default 1, from 0.2 to 30. A larger Crawl-delay in the site's robots.txt (up to 10 s) takes precedence.", "default": 1 } } }, "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 } } } } } } } } } }