x402
utility

Extract English machine-printed text from one caller-supplied PNG, JPEG, or WebP for $0.01 USDC. Call when you need local OCR without a vision API—not handwriting, not a URL fetch, and not a paid cloud OCR provider. Returns bounded text, confidence, and a SHA-256 receipt. No API key, no subscription.

post/api/v1/x402/image-ocr

Request

  • Base URL: https://api.delx.ai
  • URL: https://api.delx.ai/api/v1/x402/image-ocr
  • Auth: none declared

Request body

image_base64string required

One base64-encoded PNG, JPEG, or WebP image up to 6 MiB decoded; image/* data URIs are accepted.

imagestring

Alias for image_base64.

max_charsinteger
psm3 | 6 | 11

Tesseract page segmentation mode for machine-printed text.

Response

Paid utility result. Downstream tool errors are returned as structured result payloads with HTTP 200 after payment succeeds.

schema'delx/ocr/v1' required
scope'image_ocr' required
document_idstring required
input_sha256string required
output_sha256string required
bytesinteger required
textstring required
charsinteger required
words_observedinteger required
confidencenumber nullable required
language'eng' required
psminteger required
pages_observed1 required
total_pagesinteger nullable
truncatedboolean required
provider'first-party' required
model'tesseract-5' required
upstream_cost_usd0
sale_price_usdc0.01 required
gross_margin_floor_usd0.0097375

Legacy name for estimated marginal margin under the host allocation; not a guaranteed or realized floor.

attributionstring

Changes

No recorded changes to this operation across all 1 revision of this API.