{ "openapi": "3.0.1", "info": { "title": "Google Lens OCR API - Image to Text, Handwriting & Translation", "description": "Turn image URLs into text with Google Lens OCR. Get the full text, paragraphs with lines, optional word bounding boxes and an optional translation for scans, screenshots, photos and handwriting. Built for developers, data teams and document workflows. Pay per image read.", "version": "0.2", "x-build-id": "FJxjy4a75nChFdcF1" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/s-r~google-lens-ocr/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-s-r-google-lens-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/s-r~google-lens-ocr/runs": { "post": { "operationId": "runs-sync-s-r-google-lens-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/s-r~google-lens-ocr/run-sync": { "post": { "operationId": "run-sync-s-r-google-lens-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "image_urls" ], "properties": { "image_urls": { "title": "Image URLs", "minItems": 1, "type": "array", "description": "Direct URLs of images to OCR (JPG, PNG, WEBP, TIFF, GIF…). One per line, up to 200 per run; URLs past the 200th are reported as unprocessed. Each URL is downloaded here with a browser User-Agent and then sent to Google Lens, so the link must serve the image file itself, not a page that displays it. A URL that 403s, times out or turns out not to be an image is recorded in the run's errors key and produces no dataset row, so fewer rows than URLs is normal and worth checking there.", "items": { "type": "string" } }, "ocr_language": { "title": "OCR language hint", "type": "string", "description": "Two-letter language hint for recognition (en, nl, de, fr, ja, zh…). Lens auto-detects, this only nudges it. It does not filter the output: text in other scripts on the same image still comes back, and the value you passed is echoed on every row as ocr_language, which reflects your input rather than what Lens actually detected.", "default": "en" }, "translate_to": { "title": "Translate to", "type": "string", "description": "Optional: translate the recognized text to this two-letter language code (e.g. 'en', 'nl'). Leave empty for OCR only. The translation is done by Google Lens inside the same request, not locally afterwards, so it costs no extra call. It adds to the row rather than replacing anything: full_text, the paragraphs list and the word boxes all stay in the language on the image, and the translation arrives as a separate translated_text field. Leave this blank and no translated_text key is written at all." }, "include_word_boxes": { "title": "Include word-level bounding boxes", "type": "boolean", "description": "Emit every word with its normalized geometry (center, size, rotation). Turn off for smaller output. Switching it off only drops the words array: word_count, full_text and the per-paragraph geometry are still returned, and the request to Google is identical either way, so this changes payload size and not runtime or cost.", "default": true } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }