{ "openapi": "3.0.1", "info": { "title": "Hugging Face Hub API — Models, Datasets, Spaces", "description": "Scrape Hugging Face Hub models, datasets, and Spaces via the official public API. Downloads, likes, trending score, licenses, gated status, tasks, files, and health signals. No API key.", "version": "1.0", "x-build-id": "h8MrW4FeJqz1Pepf0" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/lmhsolutions~huggingface-hub-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-lmhsolutions-huggingface-hub-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/lmhsolutions~huggingface-hub-scraper/runs": { "post": { "operationId": "runs-sync-lmhsolutions-huggingface-hub-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/lmhsolutions~huggingface-hub-scraper/run-sync": { "post": { "operationId": "run-sync-lmhsolutions-huggingface-hub-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "resourceTypes": { "title": "Resource types", "type": "array", "description": "Which Hub resources to scrape. Competitors usually cover only models — this Actor does models, datasets, and Spaces in one run.", "items": { "type": "string", "enum": [ "models", "datasets", "spaces" ], "enumTitles": [ "Models", "Datasets", "Spaces" ] }, "default": [ "models", "datasets", "spaces" ] }, "search": { "title": "Search query", "type": "string", "description": "Substring search across repo names and authors (e.g. llama, whisper, squad)." }, "author": { "title": "Author / organization", "type": "string", "description": "Limit to one author or org (e.g. meta-llama, openai, huggingface)." }, "filter": { "title": "Tag filter", "type": "string", "description": "Hub tag filter such as text-generation, license:mit, or task_categories:question-answering." }, "sort": { "title": "Sort by", "enum": [ "downloads", "likes", "trendingScore", "lastModified", "createdAt" ], "type": "string", "description": "Sort field. trendingScore is great for discovery; downloads for popularity.", "default": "downloads" }, "direction": { "title": "Sort direction", "enum": [ "-1", "1" ], "type": "string", "description": "Use -1 for descending (most popular / newest first).", "default": "-1" }, "repoIds": { "title": "Exact repo IDs", "type": "array", "description": "Optional exact Hub repo IDs to enrich (e.g. openai/gpt-oss-120b). When set, search is still run unless skipSearch is true.", "items": { "type": "string" } }, "skipSearch": { "title": "Skip search (exact IDs only)", "type": "boolean", "description": "If true and repoIds are provided, only fetch those exact repos.", "default": false }, "maxResultsPerType": { "title": "Max results per resource type", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Cap per resource type (models / datasets / spaces). Total rows ≈ this × number of types.", "default": 25 }, "includeFull": { "title": "Include full metadata", "type": "boolean", "description": "Pass full=true to the Hub list API (tags, siblings/files, richer cards).", "default": true }, "includeConfig": { "title": "Include model config", "type": "boolean", "description": "Also request config for models (architectures, model_type).", "default": true } } }, "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 } } } } } } } } } }