The parsing response format is optimized for flexibility with retrieval augmented generation. If you are just looking for a markdown representation of a given document, you can disable chunking altogether and just use response['result']['chunks'][0]['content'].

{
    "result": {
        "type": "full",
        "chunks": [
            {
                "content": "Chunk content optimized for passing to an LLM.",
                "embed": "Chunk content optimized for passing to an embedding model.",
                "blocks": [
                    {
                        "type": "Text", // Block type (Text, Table, Figure, etc.)
                        "bbox": {
                            // All bbox values normalized to [0,1] range
                            "left": 0.1,   // Distance from left edge (10%)
                            "top": 0.2,    // Distance from top edge (20%) 
                            "width": 0.3,  // Width as % of page width (30%)
                            "height": 0.4, // Height as % of page height (40%)
                            "page": 1,     // Current page number (1-indexed)
                            "original_page": 10  // Original doc page number
                        },
                        "content": "Text content",
                        "image_url": null // presigned url to download figure/table image
                    }
                    // ...
                ]
            }
            // ...
        ]
    }
}

FAQ