Google Lens

Visual matches and related products for an image URL.


      POST
      https://api.serpkite.com/v1/lens

Credits: 2 Try in playground

View as Markdown

Google Lens for an image URL: visual matches with title, source page and thumbnails in results. The image must be publicly reachable.

Request body

Send a JSON object with Content-Type: application/json. The same parameters also work as a query string on GET /v1/lens. JSON arrays are rejected: to run many queries at once, use POST /v1/batches at half price. Unknown parameters return 400 invalid_request with a message that names the replacement; see strict validation.

Parameter	Type	Default	Description
`url` required	string		Public URL of the image. Required.
`country`	string	`us`	Country to search from, as a two-letter ISO code (us, gb, de, in…).
`language`	string	`en`	Interface language, as a language code (en, de, fr, pt-BR…).
`fields`	string		Comma-separated projection, e.g. results.title,results.link,knowledge_graph. Cuts tokens.
`max_age`	integer		Accept a cached result up to this many seconds old. Cache hits cost 50% of the credits.

Example request

Authenticate with Authorization: Bearer $SERPKITE_API_KEY (GET requests may pass ?api_key= instead). The official SDKs read SERPKITE_API_KEY for you. See Authentication.

POST /v1/lens

cURL

TypeScript

Python

curl https://api.serpkite.com/v1/lens \
  -H "Authorization: Bearer $SERPKITE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url":"https://upload.wikimedia.org/wikipedia/commons/a/a9/Example.jpg"}'

Response fields

Field	Type	Description
`request`	object	The normalised request, with defaults filled in: `endpoint`, `engine`, `q`, `country`, `language`, `location`, `num`, `page`, `device`, `autocorrect`…
`results[]`	array	Visual matches: `position`, `title`, `source`, `link`, `domain`, `image_url`, `thumbnail_url`.
`meta`	object	`request_id`, `credits_used`, `cached`, `cached_at`, `engine` (the provider that answered), `route` (provider attempts, see Search providers), `latency_ms`, `parse_quality` (`ok`, `partial`, `empty`), `resolved_urls`.

Every billed response also carries credit and latency headers (X-Credits-Used, X-Credits-Remaining, X-Request-Id…).

Example response

200 OK · illustrative

{
  "request": {
    "endpoint": "lens",
    "engine": "google",
    "url": "https://upload.wikimedia.org/wikipedia/commons/a/a9/Example.jpg",
    "country": "us",
    "language": "en"
  },
  "results": [
    {
      "position": 1,
      "title": "Example image on a product page",
      "source": "Example Shop",
      "link": "https://shop.example.com/item/42",
      "domain": "shop.example.com",
      "image_url": "https://shop.example.com/img/42.jpg",
      "thumbnail_url": "https://shop.example.com/img/42-thumb.jpg"
    }
  ],
  "meta": {
    "request_id": "req_01J8ZK4M6Q2V7",
    "credits_used": 2,
    "cached": false,
    "engine": "google",
    "latency_ms": 1034,
    "parse_quality": "ok",
    "resolved_urls": true
  }
}

Errors

Errors use one shape: {"error":{"code","message","request_id"}}. Errors are never billed. Full list in Errors.

Status	Code	Meaning
400	`invalid_request`	A parameter is missing or invalid.
401	`unauthorized`	The API key is missing, invalid or revoked.
402	`insufficient_credits`	Your balance is too low. Buy a pack or wait for the monthly free grant.
429	`rate_limited`	Too many requests per second for your plan. Retry after the Retry-After header.
503	`upstream_error`	Google could not be fetched or parsed. Not billed; retry after Retry-After.

Notes

Returns JSON only (no Markdown format).