Google Lens
Google Lens as JSON: reverse image search (the pages and products that show a picture, with prices), the pages that carry the exact picture, Google's AI answer about it, and the text in the picture read and translated into 249 languages.
/google-lens/v1/ocr2 creditsRead all text in a picture with Google Lens: the full text, its language, and paragraphs → lines → words, each with a box (fractions of the picture and pixels), writing direction and per-paragraph language; formulas come with LaTeX. Also returns the regions/objects Lens detects (boxes, no labels). One picture per call.
| Parameter | Allowed / range | Description | |
|---|---|---|---|
| image_url | optional | — | Public http(s) address of the picture (JPEG, PNG, WebP, GIF, AVIF, BMP). A web page address also works: the picture the page declares (og:image / twitter:image) is used. Give image_url OR image_base64. |
| image_base64 | optional | — | The picture itself, base64 (a data: URI is accepted), up to 20 MB decoded. Give image_url OR image_base64. |
| region | optional | — | Optional. Keep only the text inside this part of the picture: 'x,y,width,height' as fractions 0-1 of the picture (top-left origin), or in pixels when a value is above 1. Lens still reads the whole picture; words whose centre lies inside the region are returned. |
/google-lens/v1/translate2 creditsTranslate the text in a picture with Google Lens into one of 249 languages, paragraph by paragraph: original and translated text, per-paragraph status (success, no_op_translation for names, same_language…), the translated lines with their character spans, the text and background colours Lens uses to redraw the picture, and the box of every original paragraph and line.
| Parameter | Allowed / range | Description | |
|---|---|---|---|
| image_url | optional | — | Public http(s) address of the picture (JPEG, PNG, WebP, GIF, AVIF, BMP). A web page address also works: the picture the page declares (og:image / twitter:image) is used. Give image_url OR image_base64. |
| image_base64 | optional | — | The picture itself, base64 (a data: URI is accepted), up to 20 MB decoded. Give image_url OR image_base64. |
| target_language | required | — | Language to translate into: a Google Translate code such as de, ja, tr, zh-CN, pt, or the English name (German). 249 codes; the `languages` action lists them. |
| source_language | optional | — | Optional. Language of the text in the picture. Default: detected by Lens per paragraph. Setting it changes the translation (an English cover read as fr gives a different German text). |
| region | optional | — | Optional. Keep only the text inside this part of the picture: 'x,y,width,height' as fractions 0-1 of the picture (top-left origin), or in pixels when a value is above 1. Lens still reads the whole picture; words whose centre lies inside the region are returned. |
| include_background_images = false | optional | — | Also return, per translated line, the background patch Lens uses to repaint the picture with the translated text (WebP, base64; about 0.2-2 KB per line). Default false: format, size and paddings only. |
/google-lens/v1/objects2 creditsThe regions Google Lens detects in a picture — the main subject (salient region), each separate object and the whole image — with their boxes (fractions and pixels) and segmentation polygons when Lens sends them. Lens gives no label for a region.
| Parameter | Allowed / range | Description | |
|---|---|---|---|
| image_url | optional | — | Public http(s) address of the picture (JPEG, PNG, WebP, GIF, AVIF, BMP). A web page address also works: the picture the page declares (og:image / twitter:image) is used. Give image_url OR image_base64. |
| image_base64 | optional | — | The picture itself, base64 (a data: URI is accepted), up to 20 MB decoded. Give image_url OR image_base64. |
/google-lens/v1/languagesfreeThe languages Google Lens translates from and into (codes + names), as Lens itself lists them; names in the display language you choose.
| Parameter | Allowed / range | Description | |
|---|---|---|---|
| display_language = en | optional | — | Language the language NAMES are written in (en → German, tr → Almanca, de → Deutsch). |
curl -X POST https://api.reefapi.com/google-lens/v1/ocr \
-H "x-api-key: $REEF_KEY" \
-H "content-type: application/json" \
-d '{"image_url":"https://covers.openlibrary.org/b/isbn/9780140328721-L.jpg"}'{
"ok": true,
"data": { /* the result */ },
"meta": {
"latency_ms": 240,
"record_count": 12,
"completeness_pct": 100
},
"error": null
}Measured at 60 requests a second across the fleet, with no central bottleneck. Volume pricing is on request, and per-key limits are raised for high-volume accounts.
Tell us a site we do not cover yet and it becomes an engine. A customer asked for bestprice.gr on a Sunday and it was in the catalog the next day.
Median time from a question in the live chat to the first answer, measured across every answered conversation. Setup help included, no support tier to buy.
No per-site plans and no separate subscriptions. One key and one credit pool across the whole catalog, so adding a source costs nothing up front.
Planning something large? Tell us the volume and the sources and we will come back with what it costs and what we would have to build.