{ "openapi": "3.0.1", "info": { "title": "Image Similarity API | Compare Images, Find Duplicates", "description": "Compare images by visual similarity with a CLIP vision model plus perceptual hashing. Score a source image against up to 500 targets, catch exact and near-duplicates, and get one clean row per comparison. URLs, base64, or file upload. Pay per result, MCP ready for AI agents.", "version": "0.0", "x-build-id": "GBaBXxzDhKTNnLd1S" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/johnvc~image-similarity-api/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-johnvc-image-similarity-api", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/johnvc~image-similarity-api/runs": { "post": { "operationId": "runs-sync-johnvc-image-similarity-api", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/johnvc~image-similarity-api/run-sync": { "post": { "operationId": "run-sync-johnvc-image-similarity-api", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "sourceImage": { "title": "Source image", "type": "string", "description": "Provide the reference image every target is compared against: a public http(s) URL, a data:image/...;base64 URI, or raw base64 bytes. For files on your computer, use Upload source image instead." }, "sourceImageUpload": { "title": "Upload source image", "type": "array", "description": "Click Upload new files and pick the reference image from your computer, or paste a link to a file already stored on Apify. When set, this takes priority over Source image." }, "targetImages": { "title": "Target images", "type": "array", "description": "List the images to compare against the source, up to 500 per run. Each entry is an http(s) URL, a data:image base64 URI, or an object like {\"url\": \"https://...\", \"customId\": \"sku-1\", \"headers\": {\"Referer\": \"https://...\"}} for per-image tracking ids and request headers." }, "comparisonMode": { "title": "Comparison mode", "enum": [ "both", "embedding", "phash" ], "type": "string", "description": "Choose what to compute per pair. 'Semantic + duplicate detection' runs the vision model and perceptual hashes and is right for most runs. 'Semantic only' scores conceptual similarity without duplicate checks. 'Duplicate detection only' skips the model entirely, which is the fastest and cheapest way to find exact or near-exact copies.", "default": "both" }, "threshold": { "title": "Similarity threshold", "minimum": 0, "maximum": 1, "type": "number", "description": "Set the cosine similarity cutoff, 0 to 1, above which a pair is flagged isSimilar. 0.85 works well for most content; raise it toward 0.95 to keep only near-identical scenes, lower it toward 0.75 to catch loosely related images.", "default": 0.85 }, "phashThreshold": { "title": "Duplicate distance threshold", "minimum": 0, "maximum": 64, "type": "integer", "description": "Set the maximum perceptual hash Hamming distance, 0 to 64, at which a target counts as a near-duplicate of the source. 8 catches resized, recompressed, and lightly edited copies; 0 requires a pixel-structure-identical image; 12 tolerates heavier edits like small watermarks.", "default": 8 }, "sourceImageId": { "title": "Source image ID", "type": "string", "description": "Attach your own identifier for the source image; it is echoed on every result row so downstream systems can join results back to your records." }, "customId": { "title": "Custom ID", "type": "string", "description": "Attach a run-level identifier echoed on every result row. Per-target customId values inside targetImages objects override this for their row." }, "headers": { "title": "Request headers", "type": "object", "description": "Send extra HTTP headers with every image download, for example a Referer or an Authorization header for protected images. Per-target headers inside targetImages objects are merged on top for their request." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Route image downloads through Apify Proxy or your own proxies. Leave off for most runs; turn on when image hosts block datacenter traffic." } } }, "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 } } }, "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 } } } } } } } } } }