API reference

Reverse-image search

Find where an image appears online + visually similar images.

POST/api/v1/reverse-image

Scope: search
Formats: JSON · SSE
Sandbox: Free fixtures

curl https://deepsearch.app/api/v1/reverse-image \  -H "Authorization: Bearer $DEEPSEARCH_API_KEY" \  -H "Content-Type: application/json" \  -d '{        "imageUrl": "https://upload.wikimedia.org/wikipedia/commons/a/a4/Ada_Lovelace_portrait.jpg"      }'

Example request

Authorization

Authorizationheaderrequired

Send Bearer $DEEPSEARCH_API_KEY with the search scope. The free sandbox uses the published test key.

Authentication guide

Body parameters

imageUrlstringrequired

An https URL to the image to search. DeepSearch fetches and re-hosts it privately, then queries the reverse-image provider with a short-lived signed URL.

formatenum

json collects the result; sse streams progress and result events.

jsonsse

Default: json

sandboxboolean

Return deterministic, unmetered fixtures.

Default: false

Response

JSON responses preserve the operation result and include request metadata, usage, and collected events. SSE delivers progress and result events as they arrive.

Streaming & formats

{  "object": "reverse_image_result",  "request_id": "req_01HZY8Q2RVIMG9F4X9J7Z1H3AB",  "result": {    "provider": "serpapi-lens",    "matches": [      {        "url": "https://en.wikipedia.org/wiki/Ada_Lovelace",        "title": "Ada Lovelace - Wikipedia",        "sourceDomain": "en.wikipedia.org"      }    ],    "similar": [      {        "imageUrl": "https://example.com/portrait-variant.jpg",        "sourceUrl": "https://example.com/article",        "sourceDomain": "example.com"      }    ]  },  "metadata": {    "api_version": "v1",    "operation": "reverse_image",    "request_id": "req_01HZY8Q2RVIMG9F4X9J7Z1H3AB",    "generated_at": "2026-10-01T12:00:00.000Z"  },  "usage": {    "metered": true,    "credits": 1,    "cached": false  },  "events": []}

Example responseapplication/json

Sources & coverage

Submit an image URL and get candidate public pages, match provenance, and visually similar images. Provider candidates require verification; visual resemblance alone does not establish image reuse. Honest image-appearance matching - DeepSearch does NOT perform facial recognition and never identifies a person from their face. The image is re-hosted privately before it reaches the provider. Reverse-image lookup is Medium usage.

Usage & caching

Reverse-image lookup is Medium usage; idempotent replays use no usage.

Usage & rate limits

Examples illustrate the contract. Test request runs the selected deployment; sandbox fixtures are unmetered.