PreteWorks API

Render a full HTML document to a PDF. External subresources are blocked for safety — inline images/fonts as data: URIs. Returns a file_id (for chaining) and a ~1h download URL.

{
  "type": "object",
  "properties": {
    "html": {
      "type": "string",
      "description": "The complete HTML document to render."
    }
  },
  "required": [
    "html"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Stamp a page number on every page. position: bottom-center (default) | bottom-left | bottom-right | top-center | top-left | top-right. format supports {n} and {total}. Returns a file_id + ~1h URL.

{
  "type": "object",
  "properties": {
    "pdf": {
      "type": "string",
      "description": "A file_id from a prior tool result, or a base64-encoded PDF."
    },
    "position": {
      "description": "Where to place it (default bottom-center).",
      "type": "string"
    },
    "start": {
      "description": "First page's number (default 1).",
      "type": "number"
    },
    "format": {
      "description": "e.g. '{n}' or '{n} / {total}' (default '{n}').",
      "type": "string"
    }
  },
  "required": [
    "pdf"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Read a PDF's metadata (title, author, subject, keywords, creator, producer, dates) plus page count and page size, as JSON.

{
  "type": "object",
  "properties": {
    "pdf": {
      "type": "string",
      "description": "A file_id from a prior tool result, or a base64-encoded PDF."
    }
  },
  "required": [
    "pdf"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Set a PDF's title, author, subject, keywords (array or comma string) and/or creator. Only the fields you provide change. Returns a file_id + ~1h URL.

{
  "type": "object",
  "properties": {
    "pdf": {
      "type": "string",
      "description": "A file_id from a prior tool result, or a base64-encoded PDF."
    },
    "title": {
      "type": "string"
    },
    "author": {
      "type": "string"
    },
    "subject": {
      "type": "string"
    },
    "keywords": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        }
      ]
    },
    "creator": {
      "type": "string"
    }
  },
  "required": [
    "pdf"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Render a structured document to a PDF from a named template (invoice, receipt, report). Money/totals are computed for you. Returns a file_id (for chaining) and a ~1h download URL.

{
  "type": "object",
  "properties": {
    "template": {
      "type": "string",
      "enum": [
        "invoice",
        "receipt",
        "report"
      ],
      "description": "Document template."
    },
    "data": {
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {},
      "description": "Template data. invoice/receipt: {seller:{name,address?,email?,logo_url?(data: URI)}, buyer?:{name,address?,email?}, number?, issued?/date?, due?, currency?, items:[{description,qty,unit_price}], tax_rate?, notes?, terms?}; receipt also takes amount_paid?, payment_method?. report: {title, subtitle?, author?, date?, sections:[{heading?,body?}]}. Money is computed server-side."
    }
  },
  "required": [
    "template",
    "data"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Combine 2+ PDFs into a single PDF, in the order given. Inputs are file_ids (from prior tools) or base64 PDFs. Returns a file_id (for chaining) and a ~1h download URL.

{
  "type": "object",
  "properties": {
    "pdfs": {
      "minItems": 2,
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "2+ PDF sources. Each: A file_id from a prior tool result, or a base64-encoded PDF."
    }
  },
  "required": [
    "pdfs"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Keep only the specified pages of a PDF (e.g. [1,3,5]) and drop the rest, preserving order. Returns a file_id (for chaining) and a ~1h download URL.

{
  "type": "object",
  "properties": {
    "pdf": {
      "type": "string",
      "description": "A file_id from a prior tool result, or a base64-encoded PDF."
    },
    "pages": {
      "type": "string",
      "description": "Pages to keep, e.g. '1,3,5-7'."
    }
  },
  "required": [
    "pdf",
    "pages"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Rotate every page of a PDF by 90, 180, or 270 degrees (clockwise). Returns a file_id (for chaining) and a ~1h download URL.

{
  "type": "object",
  "properties": {
    "pdf": {
      "type": "string",
      "description": "A file_id from a prior tool result, or a base64-encoded PDF."
    },
    "degrees": {
      "type": "number",
      "description": "90, 180, or 270."
    }
  },
  "required": [
    "pdf",
    "degrees"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Stamp a diagonal grey text watermark (e.g. "DRAFT", "CONFIDENTIAL") across every page of a PDF. Returns a file_id (for chaining) and a ~1h download URL.

{
  "type": "object",
  "properties": {
    "pdf": {
      "type": "string",
      "description": "A file_id from a prior tool result, or a base64-encoded PDF."
    },
    "text": {
      "type": "string",
      "description": "The watermark text."
    }
  },
  "required": [
    "pdf",
    "text"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Extract the text content of a PDF — for RAG, summarization, or search. Accepts a file_id (from a prior tool) or a base64-encoded PDF, and returns the text inline. Not OCR: a scanned/image-only PDF returns little or no text.

{
  "type": "object",
  "properties": {
    "pdf": {
      "type": "string",
      "description": "A file_id from a prior tool result, or a base64-encoded PDF."
    }
  },
  "required": [
    "pdf"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Combine PNG/JPEG images (base64) into a PDF, one image per page. Returns a file_id and a ~1h URL.

{
  "type": "object",
  "properties": {
    "images": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Base64-encoded PNG/JPEG images, one per page (max 20)."
    }
  },
  "required": [
    "images"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Render Markdown to a clean, print-styled PDF. Returns a file_id and a ~1h URL.

{
  "type": "object",
  "properties": {
    "markdown": {
      "type": "string",
      "description": "The Markdown to render."
    },
    "title": {
      "description": "Document title.",
      "type": "string"
    }
  },
  "required": [
    "markdown"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Split a PDF into multiple PDFs — one per page by default, or by page ranges like '1-3;4-6'. Returns a file_id + URL per part.

{
  "type": "object",
  "properties": {
    "pdf": {
      "type": "string",
      "description": "A file_id from a prior tool result, or a base64-encoded PDF."
    },
    "ranges": {
      "description": "e.g. '1-3;4-6'. Omit to split every page.",
      "type": "string"
    }
  },
  "required": [
    "pdf"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

List a PDF's form fields (name, type, value, options) as JSON.

{
  "type": "object",
  "properties": {
    "pdf": {
      "type": "string",
      "description": "A file_id from a prior tool result, or a base64-encoded PDF."
    }
  },
  "required": [
    "pdf"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Fill a PDF's form fields from a map of field -> value; optionally flatten. Returns a file_id and a ~1h URL.

{
  "type": "object",
  "properties": {
    "pdf": {
      "type": "string",
      "description": "A file_id from a prior tool result, or a base64-encoded PDF."
    },
    "fields": {
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {},
      "description": "Map of field name to value."
    },
    "flatten": {
      "description": "Flatten the form after filling (default false).",
      "type": "boolean"
    }
  },
  "required": [
    "pdf",
    "fields"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Convert a Word (.docx), Excel (.xlsx) or CSV file (base64) into clean Markdown — for RAG, agents and pipelines. DOCX keeps headings/lists/tables; spreadsheets become Markdown tables (one per sheet). Returns Markdown inline. Optional 'format' (docx|xlsx|csv) overrides auto-detection.

{
  "type": "object",
  "properties": {
    "file": {
      "type": "string",
      "description": "Base64-encoded .docx, .xlsx or .csv file."
    },
    "format": {
      "description": "Optional format hint; auto-detected if omitted.",
      "type": "string",
      "enum": [
        "docx",
        "xlsx",
        "csv"
      ]
    }
  },
  "required": [
    "file"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Turn rows of data into a downloadable XLSX (default) or CSV. 'rows' is an array of objects (keys → header row) or an array of arrays (first row is the header). Returns a file_id (for chaining) and a ~1h download URL.

{
  "type": "object",
  "properties": {
    "rows": {
      "minItems": 1,
      "type": "array",
      "items": {},
      "description": "Array of objects (keys→columns) or array of arrays (first row = header)."
    },
    "format": {
      "description": "Output format (default xlsx).",
      "type": "string",
      "enum": [
        "xlsx",
        "csv"
      ]
    },
    "sheet_name": {
      "description": "Worksheet name (default 'Sheet1').",
      "type": "string"
    }
  },
  "required": [
    "rows"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Fetch up to 10 public URLs and return each as clean Markdown, in one call — for research/RAG over several pages at once. Private/internal hosts are blocked.

{
  "type": "object",
  "properties": {
    "urls": {
      "minItems": 1,
      "maxItems": 10,
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "1–10 http/https URLs."
    }
  },
  "required": [
    "urls"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Fetch a URL plus up to 7 more same-origin pages it links to (≤8 total), each as clean Markdown. Bounded and synchronous. Private/internal hosts are blocked.

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "The root http/https URL."
    },
    "limit": {
      "description": "Max pages incl. root (default 5, max 8).",
      "type": "integer",
      "minimum": 1,
      "maximum": 8
    }
  },
  "required": [
    "url"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Discover the same-origin URLs linked from a page — the site map, with no page content fetched. Private/internal hosts are blocked.

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "The http/https URL to map."
    }
  },
  "required": [
    "url"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Extract specified fields from a web page, PDF, or Office file as JSON, using AI. Provide 'fields' plus ONE source: a 'url', a 'pdf' (file_id or base64), or a 'file' (base64 .docx/.xlsx/.csv). Returns a JSON object mapping each field to its value, or null when absent.

{
  "type": "object",
  "properties": {
    "fields": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Field names to extract, e.g. ['invoice total','due date']."
    },
    "url": {
      "description": "A public http/https URL to read.",
      "type": "string"
    },
    "pdf": {
      "description": "A file_id from a prior tool result, or a base64-encoded PDF.",
      "type": "string"
    },
    "file": {
      "description": "A base64-encoded .docx, .xlsx or .csv file (converted to text first).",
      "type": "string"
    }
  },
  "required": [
    "fields"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Summarize a web page, PDF, Office file (.docx/.xlsx/.csv), or raw text using AI. Provide ONE source: 'url', 'pdf' (file_id or base64), 'file' (base64), or 'text'. Optional 'max_words'. Returns the summary.

{
  "type": "object",
  "properties": {
    "url": {
      "description": "A public http/https URL to read.",
      "type": "string"
    },
    "pdf": {
      "description": "A file_id from a prior tool, or a base64-encoded PDF.",
      "type": "string"
    },
    "file": {
      "description": "A base64-encoded .docx, .xlsx or .csv file.",
      "type": "string"
    },
    "text": {
      "description": "Raw text to summarize directly.",
      "type": "string"
    },
    "max_words": {
      "description": "Approximate target length in words.",
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 9007199254740991
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Answer a question grounded ONLY in a source document — a web page, PDF, Office file, or raw text. Provide 'question' plus ONE source: 'url', 'pdf', 'file' (base64), or 'text'. Says so when the answer isn't in the document.

{
  "type": "object",
  "properties": {
    "question": {
      "type": "string",
      "description": "The question to answer from the document."
    },
    "url": {
      "description": "A public http/https URL to read.",
      "type": "string"
    },
    "pdf": {
      "description": "A file_id from a prior tool, or a base64-encoded PDF.",
      "type": "string"
    },
    "file": {
      "description": "A base64-encoded .docx, .xlsx or .csv file.",
      "type": "string"
    },
    "text": {
      "description": "Raw text to answer from directly.",
      "type": "string"
    }
  },
  "required": [
    "question"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Extract the text of a .docx document (base64). Returns the text inline.

{
  "type": "object",
  "properties": {
    "docx": {
      "type": "string",
      "description": "Base64-encoded .docx file."
    }
  },
  "required": [
    "docx"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Convert a .docx document (base64) to a PDF. Returns a file_id and a ~1h URL.

{
  "type": "object",
  "properties": {
    "docx": {
      "type": "string",
      "description": "Base64-encoded .docx file."
    }
  },
  "required": [
    "docx"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Fetch a public http/https URL and return its main content as clean Markdown — ideal for giving an agent readable web content for research or RAG. Private/internal hosts are blocked.

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "The http/https URL to read."
    }
  },
  "required": [
    "url"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Fetch a public http/https URL and render the live page to a PDF. Returns a file_id (chainable into the PDF tools) and a ~1h download URL. Private/internal hosts are blocked.

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "The http/https URL to snapshot."
    }
  },
  "required": [
    "url"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Fetch a public http/https URL and capture a PNG screenshot. Set full_page for the entire scroll height. Returns a file_id and a ~1h download URL.

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "The http/https URL to capture."
    },
    "full_page": {
      "description": "Capture the full scroll height (default: viewport).",
      "type": "boolean"
    }
  },
  "required": [
    "url"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Fetch a public http/https URL and return its rendered HTML, the links on the page, and page metadata (title/description/OpenGraph/canonical/favicon) — in one render. For clean Markdown use read_url instead. Private/internal hosts are blocked.

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "The http/https URL to scrape."
    },
    "formats": {
      "description": "Which representations to return (default: all three).",
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "html",
          "links",
          "metadata"
        ]
      }
    }
  },
  "required": [
    "url"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}