{ "openapi": "3.0.1", "info": { "title": "Hugging Face Scraper - Models, Datasets, Spaces", "description": "List and rank Hugging Face models, datasets and spaces by downloads, likes or trending score. Filter by task, author or search term. Returns licence, languages, base model, file list, gated status and dates from the official Hub API.", "version": "0.1", "x-build-id": "Sxi0VOhLVDJa3mIZg" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/s-r~huggingface-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-s-r-huggingface-scraper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/s-r~huggingface-scraper/runs": { "post": { "operationId": "runs-sync-s-r-huggingface-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/s-r~huggingface-scraper/run-sync": { "post": { "operationId": "run-sync-s-r-huggingface-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "repo_type": { "title": "What to list", "enum": [ "models", "datasets", "spaces" ], "type": "string", "description": "Models, datasets or spaces. The same filters and sorts apply to all three.", "default": "models" }, "search": { "title": "Search term", "type": "string", "description": "Free-text search over repo names, for example llama or whisper." }, "task": { "title": "Task filter", "type": "string", "description": "Filter models by task tag, for example text-generation, text-classification or automatic-speech-recognition." }, "author": { "title": "Author or organisation", "type": "string", "description": "Only repos owned by this user or organisation, for example openai or meta-llama." }, "repo_ids": { "title": "Specific repo IDs", "type": "array", "description": "Look up named repos directly instead of listing, for example openai/whisper-large-v3. This always fetches full detail, so licence and file list are populated.", "items": { "type": "string" } }, "sort": { "title": "Sort by", "enum": [ "downloads", "likes", "lastModified", "createdAt", "trendingScore" ], "type": "string", "description": "Which repos come first.", "default": "downloads" }, "direction": { "title": "Order", "enum": [ "desc", "asc" ], "type": "string", "description": "Descending puts the most downloaded or newest first.", "default": "desc" }, "detail": { "title": "Fetch full detail", "type": "boolean", "description": "Make one extra call per repo to fill in licence, languages and the file list. Listings do not carry those. Slower and uses more of the rate-limit window.", "default": false }, "token": { "title": "Hugging Face token (optional)", "type": "string", "description": "Only needed for private or gated repos. Public listing works without one and the rate limit is the same." }, "limit": { "title": "Maximum repos", "minimum": 1, "maximum": 3000, "type": "integer", "description": "How many repos to return.", "default": 100 }, "retries": { "title": "Retries per request", "minimum": 1, "maximum": 6, "type": "integer", "description": "Retries with backoff before a request is reported as an error.", "default": 3 } } }, "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 } } } } } } } } } }