Parse in the Playground

Use the Playground to upload a document, see what the Parse v2 API returns, and copy a ready-to-use API snippet before you write any code.

​

Parse a Document in the Playground

To parse a document with :

1. Go to the Playground.
2. In the upload card, click the model drop-down menu and select DPT-3 Pro.
3. Drag and drop your file into the upload area, or click to choose a file.
4. Click Start. The Playground processes the file and opens the project view with the parse results.

​

Review the Results

The parse results open in the Parse tab of the project view:

• Markdown view (default): The reading-order Markdown rendering of your document. Use this for quick visual review or to copy into a downstream tool.
• JSON view: The full response payload. Use this view to inspect block ids, spans, and grounding coordinates.
• Click a block in either view to highlight its bounding box on the document preview on the left.
• Use the Download and Copy buttons in the toolbar above the result to save or paste the current view.

For a complete reference on what each response field contains, see Parse API Response.

​

Customize the Parse Output with Config

To change how parses your files, open the Config drop-down menu on the Parse tab and update the settings. These controls set the same values as the API’s options field. After you adjust the options, click Apply to all files to reparse with the new settings.

• Captioning options: Choose which block types are included in the Markdown (Text, Table, Figure, Attestation, Marginalia, Card, and Scan code). All are on by default. Clearing one drops that block type’s content from the Markdown, but the block still appears in the JSON structure and grounding.
• Table output format: Choose HTML (default) or Markdown for how tables appear in the Markdown output. This control appears only while Table captioning is on.
• Fine-grained output: Include the per-line grounding detail (the parts array) with each block. On by default.
• Pages: Enter the pages to parse (for example, 1-3) to process only part of the document. The Playground uses 1-based page numbers; the API’s options.pages uses 0-based indices.

​

Get a Ready-to-Use Code Snippet

When the parse results match what you need, click Get Code in the project header to open a Python snippet that reproduces the call against the API. Copy it into your own project to parse the same document, or any other, from code.