{"uid":"cap_tvvxK-fjyytV_370P5ezB","slug":"delx-image-ocr-363ac012","name":"Delx Image OCR","description":"Delx is an independent AI agent lab building and studying continuity, recovery, verifiable work and governed exchange for autonomous systems.","url":"https://api.delx.ai/api/v1/x402/image-ocr?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"psm":{"enum":[3,6,11],"type":"integer","default":6,"description":"Tesseract page segmentation mode for machine-printed text."},"image":{"type":"string","maxLength":8388608,"minLength":1,"description":"Alias for image_base64."},"max_chars":{"type":"integer","default":200000,"maximum":200000,"minimum":1,"description":"Maximum UTF-8 characters returned; OCR remains bounded."},"image_base64":{"type":"string","maxLength":8388608,"minLength":1,"description":"One base64-encoded PNG, JPEG, or WebP image up to 6 MiB decoded; image/* data URIs are accepted."}}},"responseSchema":{"type":"json","example":{"psm":6,"text":"Printed text recognized from the image","bytes":48210,"chars":39,"model":"tesseract-5","scope":"image_ocr","schema":"delx/ocr/v1","language":"eng","provider":"first-party","truncated":false,"confidence":96.42,"attribution":"Text recognized locally by Delx with Tesseract; no image is stored, fetched, or sent to a third-party provider.","document_id":"image_8b4d5e6f7a8b9c0d1e2f3a4b5c6d7e8f","total_pages":1,"input_sha256":"8b4d5e6f7a8b9c0d1e2f3a4b5c6d7e8f901234567890abcdef1234567890ab","output_sha256":"c5f7b2d4c1e7a0f9b6d2e8c3a4f5b6071234567890abcdef1234567890abcdef","pages_observed":1,"words_observed":7,"sale_price_usdc":0.01,"upstream_cost_usd":0,"gross_margin_floor_usd":0.0097375}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_dh0F1E2fhPKHGJNPny-sd","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts machine-printed English text from a base64-encoded PNG, JPEG, or WebP image using local Tesseract OCR, returning the text, confidence score, and a SHA-256 receipt for $0.01 USDC via x402.","exampleAgentPrompt":"Can you extract all the printed text from this invoice image I'm sending you as a base64-encoded JPEG? Use page segmentation mode 6 and return up to 50000 characters.","exampleUseCases":[{"title":"Digitize printed invoice for accounting","prompt":"I have a scanned invoice as a base64 JPEG — can you run OCR on it with segmentation mode 6 and pull out all the printed text so I can parse the line items?"},{"title":"Extract text from screenshot for search","prompt":"Here's a PNG screenshot of a document I need to search through — please extract all the machine-printed text from it using mode 3 so I can run keyword queries on it."},{"title":"Read printed form fields from scanned page","prompt":"I've got a base64-encoded WebP of a printed government form; can you OCR it with page segmentation mode 11 and give me the text along with a confidence score?"}],"resultDescription":"Returns the extracted machine-printed English text (bounded by max_chars), a confidence score indicating OCR reliability, and a SHA-256 receipt for payment verification. No external storage or vision provider is used; processing is local.","failureModes":["Image exceeds 6 MiB decoded size — returns an error rejecting the payload","Unsupported image format (non-PNG/JPEG/WebP) — returns a format error","Low-confidence result for handwritten, stylized, or non-English text — returned text may be garbled","max_chars truncation silently caps the output without error","Invalid base64 encoding — returns a decode error","Payment failure or invalid x402 token — returns a 402 or auth error"],"whenToPreferThis":"Choose this endpoint when you need lightweight, low-cost ($0.01 USDC) machine-printed English OCR on a single image without any external API calls, data storage, or reliance on a paid cloud vision provider. It is ideal for agent pipelines that handle sensitive documents locally, need a cryptographic SHA-256 receipt per call, or operate on constrained budgets. Prefer alternatives if you need handwriting recognition, multi-language OCR, or PDF-native parsing.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-16T00:52:20.916Z","isFirstParty":false,"canonicalSlug":"delx-image-ocr-363ac012"}