{"slug":"voice-madebydevx-com-v1-ocr-519eeb","title":"OCR for agents","host":"voice.madebydevx.com","method":"POST","resource":"https://voice.madebydevx.com/v1/ocr","category":"image","description":"OCR for agents: send an image URL or base64 (PNG, JPEG, WebP, GIF; up to 3 MB) and get the text it contains in reading order, as plain text or Markdown (tables, lists). Works on screenshots, receipts, invoices, signs and documents. $0.002 USDC per image on Base; images with no readable text are not ","price_listed":0.002,"price_asked":null,"state":"effects","state_label":"Not tested: has real-world effects","checks_7d":0,"answered_7d":0,"latency_ms_median":null,"reported_calls_30d":1,"reported_payers_30d":1,"networks":["eip155:8453"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"body":{"image_url":"https://voice.madebydevx.com/samples/invoice.png"},"bodyType":"json","discoverable":true,"method":"POST","type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"additionalProperties":false,"properties":{"format":{"description":"Output format (default text)","enum":["text","markdown"],"type":"string"},"image_base64":{"description":"Base64 image; a data: URI prefix is allowed","type":"string"},"image_url":{"description":"Public http(s) URL of the image (max 3 MB)","type":"string"},"language_hint":{"description":"Optional expected language","maxLength":40,"type":"string"},"requestKey":{"description":"Optional idempotency key: the same payer + requestKey + input within 7 days returns the stored result without a second charge.","maxLength":128,"minLength":8,"pattern":"^[A-Za-z0-9][A-Za-z0-9._:-]{7,127}$","type":"string"}},"type":"object"},"bodyType":{"enum":["json"],"type":"string"},"discoverable":{"type":"boolean"},"method":{"enum":["POST"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"properties":{"operation_id":{"type":"string"},"payment":{"type":"object"},"result":{"type":"object"},"status":{"type":"string"}},"required":["operation_id","status","result"],"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"},"history":[],"description_full":"OCR for agents: send an image URL or base64 (PNG, JPEG, WebP, GIF; up to 3 MB) and get the text it contains in reading order, as plain text or Markdown (tables, lists). Works on screenshots, receipts, invoices, signs and documents. $0.002 USDC per image on Base; images with no readable text are not charged. Gemma 4 vision. By DevX.","last_updated":"2026-10-22T14:43:06.824Z","schemes":["exact"]}