{"slug":"agent402-tools-api-image-ocr-b80244","title":"Extract text from a PNG or JPEG image","host":"agent402.tools","method":"POST","resource":"https://agent402.tools/api/image-ocr","category":"image","description":"Extract text from a PNG or JPEG image - full text, overall confidence and per-line bounding boxes - from a URL or base64 payload, Tesseract on-device (no upstream API). Default English; other ISO 639-2 languages on request. Use it when an agent needs the words in a screenshot, scan or photo.","price_listed":0.01,"price_asked":0.01,"state":"answering","state_label":"Answering","checks_7d":1,"answered_7d":1,"latency_ms_median":952,"reported_calls_30d":5,"reported_payers_30d":1,"networks":["algorand:wGHE2Pwdvd7S12BL5FaOP20EGYesN73ktiC1qzkkit8=","eip155:10","eip155:1329","eip155:137","eip155:143","eip155:42161","eip155:42220","eip155:43114","eip155:4663","eip155:8453","solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp","stellar:pubnet"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"body":{"url":"https://tesseract.projectnaptha.com/img/eng_bw.png"},"bodyType":"json","method":"POST","type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"properties":{"image":{"description":"Base64 PNG/JPEG (data: URL prefix accepted). Either this or url is required.","type":"string"},"lang":{"description":"Language code, ISO 639-2. Default 'eng'. Supported: eng, spa, fra, deu, ita, por, nld, rus, pol, tur, chi_sim, chi_tra, jpn, kor, ara, hin, tha, vie, ukr, ell.","type":"string"},"url":{"description":"HTTPS URL to fetch the image from (max 8 MB). Either this or image is required.","type":"string"}}},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"properties":{"confidence":{"type":"number"},"lang":{"type":"string"},"lineCount":{"type":"integer"},"lines":{"items":{"properties":{"bbox":{"properties":{"x0":{"type":"integer"},"x1":{"type":"integer"},"y0":{"type":"integer"},"y1":{"type":"integer"}},"type":"object"},"confidence":{"type":"number"},"text":{"type":"string"}},"type":"object"},"type":"array"},"source":{"type":"string"},"text":{"type":"string"}},"required":["text","confidence","lang","lineCount","lines","source"],"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"},"history":[{"day":"2026-09-24","reachable":true,"status":402,"valid_402":true,"asked_usdc":0.01,"price_match":true,"latency_ms":952,"error":null}],"description_full":"Extract text from a PNG or JPEG image - full text, overall confidence and per-line bounding boxes - from a URL or base64 payload, Tesseract on-device (no upstream API). Default English; other ISO 639-2 languages on request. Use it when an agent needs the words in a screenshot, scan or photo.","last_updated":"2026-09-22T09:23:52.504Z","schemes":["exact","upto"]}