{"service":"doc-extract","currency":"USDC","network":"eip155:8453","network_name":"Base Mainnet","pay_to":"0x2880EdfFF13100677Bf97A3CBdF3Bc34771C4E5E","model":"per page","settlement":"per request, no account, no API key","unit_price_usdc":{"text_layer_page":"0.02","ocr_page":"0.05","ocr_image_or_first_page":"0.006","ocr_further_page":"0.002"},"limits":{"max_pages_per_call":20,"hard_time_limit_seconds":60,"max_document_bytes":15728640,"cache_ttl_seconds":86400,"ocr_max_pages_per_call":50,"ocr_hard_time_limit_seconds":85,"ocr_max_bytes":12582912,"ocr_max_width_pixels":10000},"max_price_per_call_usdc":"1.000000","endpoints":[{"method":"POST","path":"/document","pricing":"per page","price_text_page_usdc":"0.02","price_ocr_page_usdc":"0.05","max_price_per_call_usdc":"1.000000","tool":"extract_document","summary":"Turn one PDF into structured JSON: header fields, tables as rows and columns, key value pairs and per page full text, each field with its page, position and confidence."},{"method":"POST","path":"/ocr","pricing":"per image, further pages cheaper","price_first_page_usdc":"0.006","price_further_page_usdc":"0.002","max_price_per_call_usdc":"0.104000","tool":"ocr_read","summary":"Read a picture, a scan or a screenshot: full text in reading order, typed blocks with their box on the page, tables as a matrix plus markdown, and every QR code and barcode with its decoded content."}],"notes":["The first call without a payment header answers 402 and carries the exact price for the file that was sent.","Only the pages actually processed are settled. A page range narrows both the work and the price.","POST /ocr charges 0.006 USDC for one image or the first page of a PDF and 0.002 USDC for every further page, at most 50 pages per call.","A cached answer costs the same and simply arrives faster. The cache expires after 24 hours per file checksum and options.","A failed extraction is rejected before settlement, so a failure is never charged. A recognition that comes back empty counts as a failure."]}