Convert PDF and Word files to Markdown

Give your Agent a publicly retrievable HTTPS document link, up to 25 MB, to request a Markdown document. Choose OCR for scanned PDF text and set your hyperlink, image-reference and content preferences.

Your AI

Use with your AI

For tasks with several steps, continue in the AI you already use.

CodexClaude CodeCursorWindsurfCline

View instructions

Use parse-file-to-markdown-context-dev with a publicly accessible HTTPS file link no larger than 25 MB. Ask the user for a file link they can share without sign-in, not a technical URL or file field. If they provide a familiar cloud-sharing link, resolve it only through a known method and confirm it retrieves the file before submitting; never guess access tokens or bypass permissions. If the link asks for sign-in or opens a sharing page instead of the file, explain in simple words how to enable “anyone with the link can view or download” or ask for a direct file link. Infer file type from the link or response when possible; if unclear, ask whether it is a PDF, Word or Excel file. Preserve links by default and include pictures only when requested. If the user asks to read text in scanned PDF pages, enable text recognition and check that its additional fee fits their existing budget. Reuse the existing Toolmu connection, follow the page setup guide if needed, and stay within the agreed budget and current price. Show the document resource, available download link, link/file expiry separately and whether text recognition actually ran. Compare retrieved text with the source when available, and say when pages or words may be missing.

Task:
Read [a file link anyone can open], up to 25 MB. Turn it into an easy-to-read document, keep links and pictures where possible, and try to read words from PDF pages that are scans or photos.

Paste into your connected AI's conversation.

Connection guide

Up to 0.0054 credits / call

The final charge is based on confirmed usage. Unused reserved credits return to your available balance.

Context.dev

Convert PDF and Word files to Markdown

You receive

Receive a converted Markdown document resource, with its content type, temporary download reference, separate file/link expiry times and reported OCR status. You or your Agent can retrieve an available valid result for use in notes, documents or further reading.

Start with your task

Read [a file link anyone can open], up to 25 MB. Turn it into an easy-to-read document, keep links and pictures where possible, and try to read words from PDF pages that are scans or photos.

What to know

Conversion and OCR do not guarantee every layout detail, table or image is preserved. Access links and files can expire separately, with no permanent-link guarantee. Review actual OCR status and the converted content; ZDR depends on provider authorization and applies to Context.dev’s processing.

Inputs & outputs

Inspect the current inputs, availability, and maximum charge before starting.

Input schema

Input schema
Field / Path	Type	Requirement	Meaning
Document conversion settings`body`	`object`	Required	Required file link and optional format hint, OCR, link/image preferences and provider ZDR setting. Required fields `file_url`
Request PDF OCR`body.ocr`	`boolean`	Optional	Request OCR for images embedded in PDF pages, such as scanned text. Default false. Inspect ocr_ran to see whether OCR actually ran.
Context.dev retention mode`body.zdr`	`string`	Optional	enabled requests bypassing Context.dev shared caches and omitting request/response content from its retained usage logs. It requires ZDR authorization on that provider organization; disabled does not request this mode. This setting covers Context.dev’s processing only. Options `enabled, disabled`
HTTPS file URL`body.file_url`	`string`	Required	Required publicly retrievable HTTPS file URL, up to 25 MB. A signed storage link can be used while valid; the file is fetched server-side for conversion. Format `uri`
File-format hint`body.extension`	`string`	Optional	Optional file-type hint, 1–16 characters, such as pdf, docx or xlsx, when the URL or Content-Type does not identify the format. Minimum length `1` Maximum length `16`
Preserve hyperlinks`body.includeLinks`	`boolean`	Optional	Request hyperlinks in the converted Markdown. Default true.
Include image references`body.includeImages`	`boolean`	Optional	Request image references in the converted Markdown. Default false; references do not guarantee that every image is included or permanently available.
Keep main content only`body.useMainContentOnly`	`boolean`	Optional	When enabled, retain the main content and drop detectable headers, footers, sidebars or navigation. Default false.
Shorten inline image data`body.shortenBase64Images`	`boolean`	Optional	Truncate inline base64 image payloads to reduce output size. Default true; shortened data may not be a complete reusable image.

View raw JSON

{
  "type": "object",
  "required": [
    "body"
  ],
  "properties": {
    "body": {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "file_url"
      ],
      "~standard": {
        "vendor": "zod",
        "version": 1,
        "jsonSchema": {}
      },
      "properties": {
        "ocr": {
          "type": "boolean",
          "description": "Enable OCR for images embedded in PDF pages when needed. It is off by default. Check ocr_ran in the returned result to see whether OCR actually ran, and read the current Toolmu execution ceiling before authorizing the request."
        },
        "zdr": {
          "enum": [
            "enabled",
            "disabled"
          ],
          "type": "string",
          "description": "Set 'enabled' to bypass Context.dev's shared caches and omit request and response content from its retained usage logs. Requires zero data retention on the Context.dev organization, otherwise the call fails with ZDR_NOT_ENABLED."
        },
        "file_url": {
          "type": "string",
          "format": "uri",
          "description": "Public https:// URL of the file to parse (up to 25MB — e.g. a presigned S3 link or a Monid file-system byte link). Monid fetches it server-side and relays the bytes to Context.dev."
        },
        "extension": {
          "type": "string",
          "maxLength": 16,
          "minLength": 1,
          "description": "File-type hint (e.g. 'pdf', 'docx', 'xlsx') for when the URL or its Content-Type does not reveal the format."
        },
        "includeLinks": {
          "type": "boolean",
          "description": "Preserve hyperlinks in the Markdown output. Default true."
        },
        "includeImages": {
          "type": "boolean",
          "description": "Include image references in the Markdown output. Default false."
        },
        "useMainContentOnly": {
          "type": "boolean",
          "description": "Keep only the page's main content, dropping headers, footers, sidebars, and navigation when detectable. Default false."
        },
        "shortenBase64Images": {
          "type": "boolean",
          "description": "Truncate inline base64 image payloads to keep the output small. Default true."
        }
      },
      "additionalProperties": false
    }
  },
  "additionalProperties": false
}

Result schema

No fixed output contract is available. Field types reflect saved result evidence; individual responses can differ.

Result schema
Field / Path	Type	Meaning
Detected file type`result.type`	`string`	File type reported for the converted input, such as pdf.
Conversion status`result.success`	`boolean`	Reported conversion success flag. Inspect the resulting document before relying on content accuracy or formatting.
Markdown document resource`result.document`	`object`	The converted document’s resource metadata, including content type, temporary download reference and separate file/link expiry times.
Document content type`result.document.content_type`	`string`	Content type reported for the output document, such as text/markdown.
Temporary download URL`result.document.download_link`	`null`	Download reference for accessing the converted document when available and valid. It is separate from the source file URL.
Download-link expiry`result.document.link_expires_at`	`string`	Reported time when the access link expires. Check it separately from the file’s expiry.
Document-file expiry`result.document.file_expires_at`	`string`	Reported time when the document file expires, distinct from the temporary access link’s expiry.
OCR actually ran`result.ocr_ran`	`boolean`	Whether OCR ran for this conversion. Requesting ocr true does not itself establish that OCR was performed.
Supplier OCR processing count`result.ocr_units`	`number`	Supplier-reported OCR processing count, read with ocr_ran. This is not a Toolmu wallet debit or a fixed currency price.

Questions about this tool.

Inputs, results and details to know before running it.

Get connected

Provide a publicly retrievable HTTPS link to a document no larger than 25 MB, such as a PDF or Word DOCX file. The native input uses file_url; a local file path does not supply the file. If the link or Content-Type does not reveal the format, provide an extension hint.

Convert PDF and Word files to Markdown

Convert PDF and Word files to Markdown

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Use Toolmu with your AI assistant

Share a file link

Check the result

Questions about this tool.

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Use Toolmu with your AI assistant

Share a file link

Check the result

Questions about this tool.

What file link should I provide?

Will OCR run, and what do OCR units mean?

How long can I use the returned document link?

Will the Markdown preserve every table, image and layout detail?

What does enabling ZDR cover?