{
  "url": "https://telipot.com/catalog/capabilities/web.page.batch.start",
  "id": "web.page.batch.start",
  "description": "Start scraping a list of web pages as one job",
  "platform": "web",
  "providers": [
    {
      "slug": "firecrawl",
      "name": "Firecrawl"
    }
  ],
  "tasks": 1,
  "taskPages": [
    {
      "id": "firecrawl.web.page.batch.start",
      "name": "Start a batch scrape of many URLs; returns the job id",
      "provider": {
        "slug": "firecrawl",
        "name": "Firecrawl"
      },
      "capability": "web.page.batch.start",
      "platform": "web",
      "kind": "data",
      "tier": "core",
      "identity": "key",
      "identityLabel": "Your plan",
      "price": {
        "type": "per_result",
        "confidence": "documented",
        "source": "docs",
        "sourceUrl": "https://docs.firecrawl.dev/billing",
        "checked": "2026-10-05",
        "note": "1 credit per page, billed as each page finishes, not when the job is submitted; the status route reports creditsUsed. A PDF costs 1 credit per PDF page. The JSON and other formats that add credits are not offered by this task.",
        "state": "paid",
        "label": "$0.0038 / page",
        "amount": "$0.0038",
        "unit": "page",
        "usdPerUnit": {
          "floor": 0.0038,
          "ceiling": 0.0038
        },
        "native": {
          "text": "1 credit per page",
          "figure": "1 credit",
          "per": "page",
          "currency": "credits"
        },
        "detail": "1 credit · docs"
      },
      "providers": 1,
      "retention": "standard",
      "runsOn": "byoc",
      "live": true,
      "summary": "Scrape multiple URLs and optionally extract information using an LLM",
      "method": "POST",
      "path": "/batch/scrape",
      "host": "https://api.firecrawl.dev/v2",
      "docsUrl": "https://docs.firecrawl.dev/api-reference/endpoint/batch-scrape",
      "auth": {
        "scheme": "bearer",
        "label": "bearer · Authorization: Bearer",
        "short": "bearer · Authorization"
      },
      "scope": "any_account",
      "principal": "organization",
      "requiredScopes": [],
      "verification": {
        "state": "none",
        "label": "Not verified yet",
        "detail": "Not checked yet. We test with a real request before we mark it."
      },
      "input": [
        {
          "name": "urls",
          "location": "body",
          "type": "array",
          "required": true,
          "constraints": [],
          "note": "The URLs to scrape"
        },
        {
          "name": "ignoreInvalidURLs",
          "location": "body",
          "type": "boolean",
          "required": false,
          "constraints": [
            "default true"
          ],
          "note": "Skip invalid URLs and list them in invalidURLs instead of failing the request"
        },
        {
          "name": "maxConcurrency",
          "location": "body",
          "type": "integer",
          "required": false,
          "constraints": [],
          "note": "Maximum number of concurrent scrapes; defaults to the team's concurrency limit"
        },
        {
          "name": "onlyMainContent",
          "location": "body",
          "type": "boolean",
          "required": false,
          "constraints": [
            "default true"
          ],
          "note": "Only return the main content of each page, excluding headers, navs and footers"
        },
        {
          "name": "waitFor",
          "location": "body",
          "type": "integer",
          "required": false,
          "constraints": [
            "default 0"
          ],
          "note": "Delay in milliseconds before fetching each page"
        },
        {
          "name": "maxAge",
          "location": "body",
          "type": "integer",
          "required": false,
          "constraints": [
            "default 172800000"
          ],
          "note": "Accept a cached copy younger than this many milliseconds (default 2 days)"
        },
        {
          "name": "timeout",
          "location": "body",
          "type": "integer",
          "required": false,
          "constraints": [
            "1000 to 300000",
            "default 60000"
          ],
          "note": "Timeout in milliseconds"
        },
        {
          "name": "mobile",
          "location": "body",
          "type": "boolean",
          "required": false,
          "constraints": [
            "default false"
          ],
          "note": "Emulate scraping from a mobile device"
        },
        {
          "name": "proxy",
          "location": "body",
          "type": "string",
          "required": false,
          "constraints": [
            "one of \"basic\", \"enhanced\", \"auto\"",
            "default \"auto\""
          ],
          "note": "auto retries with enhanced proxies when basic fails; enhanced is billed like basic"
        }
      ],
      "sampleInput": {
        "urls": [
          "https://example.com"
        ]
      },
      "inputSchema": {
        "type": "object",
        "properties": {
          "urls": {
            "type": "array",
            "description": "The URLs to scrape",
            "examples": [
              [
                "https://example.com"
              ]
            ]
          },
          "ignoreInvalidURLs": {
            "type": "boolean",
            "description": "Skip invalid URLs and list them in invalidURLs instead of failing the request",
            "default": true
          },
          "maxConcurrency": {
            "type": "integer",
            "description": "Maximum number of concurrent scrapes; defaults to the team's concurrency limit"
          },
          "onlyMainContent": {
            "type": "boolean",
            "description": "Only return the main content of each page, excluding headers, navs and footers",
            "default": true
          },
          "waitFor": {
            "type": "integer",
            "description": "Delay in milliseconds before fetching each page",
            "default": 0
          },
          "maxAge": {
            "type": "integer",
            "description": "Accept a cached copy younger than this many milliseconds (default 2 days)",
            "default": 172800000
          },
          "timeout": {
            "type": "integer",
            "description": "Timeout in milliseconds",
            "default": 60000,
            "minimum": 1000,
            "maximum": 300000
          },
          "mobile": {
            "type": "boolean",
            "description": "Emulate scraping from a mobile device",
            "default": false
          },
          "proxy": {
            "type": "string",
            "description": "auto retries with enhanced proxies when basic fails; enhanced is billed like basic",
            "enum": [
              "basic",
              "enhanced",
              "auto"
            ],
            "default": "auto"
          }
        },
        "required": [
          "urls"
        ],
        "additionalProperties": false
      },
      "output": [
        {
          "name": "success",
          "type": "boolean"
        },
        {
          "name": "id",
          "type": "string",
          "description": "The batch job id to pass to the status task"
        },
        {
          "name": "url",
          "type": "string",
          "description": "The status URL of the job"
        },
        {
          "name": "invalidURLs",
          "type": "array | null"
        }
      ],
      "outputSchema": {
        "type": "object",
        "required": [
          "success",
          "id",
          "url"
        ],
        "properties": {
          "success": {
            "type": "boolean"
          },
          "id": {
            "type": "string",
            "description": "The batch job id to pass to the status task"
          },
          "url": {
            "type": "string",
            "description": "The status URL of the job"
          },
          "invalidURLs": {
            "type": [
              "array",
              "null"
            ],
            "items": {
              "type": "string"
            }
          }
        }
      },
      "commands": {
        "mode": "run",
        "cli": "telipot run firecrawl.web.page.batch.start \\\n  --input-json '{\"urls\":[\"https://example.com\"]}'",
        "http": "curl https://api.telipot.com/v1/tasks/firecrawl.web.page.batch.start/run \\\n  -H \"Authorization: Bearer $TELIPOT_TOKEN\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"urls\":[\"https://example.com\"]}'",
        "quote": "telipot run firecrawl.web.page.batch.start \\\n  --input-json '{\"urls\":[\"https://example.com\"]}' \\\n  --quote"
      },
      "siblings": []
    }
  ]
}