Hugging Face Models & Datasets Search
Pricing
$1.00 / 1,000 hub items
Hugging Face repository search for model and dataset discovery. Export public model, dataset and Space metadata as JSON with source links.
You can access the Hugging Face Models & Datasets Search programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "1.0", "x-build-id": "18L7F43p2UGI3r7Tv" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/grit-77~hf-models/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-grit-77-hf-models", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/grit-77~hf-models/runs": { "post": { "operationId": "runs-sync-grit-77-hf-models", "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/grit-77~hf-models/run-sync": { "post": { "operationId": "run-sync-grit-77-hf-models", "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": { "query": { "title": "Search query", "type": "string", "description": "Keyword contained in repository names. Leave empty to browse by sort order." }, "resourceTypes": { "title": "Repository types", "type": "array", "description": "Choose any of models, datasets, spaces. Results are merged in this type order per page round.", "items": { "type": "string" }, "default": [ "models" ] }, "task": { "title": "Task", "type": "string", "description": "Model pipeline tag or dataset task category, e.g. fill-mask or text-classification. Spaces must publish a matching task or tag." }, "library": { "title": "Library or Space SDK", "type": "string", "description": "Model library (transformers), dataset library (datasets, pandas), or Space SDK (gradio, streamlit)." }, "author": { "title": "Author or organization", "type": "string", "description": "Exact public repository owner, e.g. google-bert." }, "license": { "title": "License", "type": "string", "description": "Exact published license identifier, e.g. apache-2.0 or mit. Matches any published license for multi-license cards." }, "tags": { "title": "Required tags", "type": "array", "description": "Exact Hub tags; all must match. At most 20 tags.", "items": { "type": "string" }, "default": [] }, "sortBy": { "title": "Sort by", "enum": [ "likes", "downloads", "lastModified", "createdAt" ], "type": "string", "description": "Hub sort order within each repository type. Downloads cannot be used when Spaces are selected.", "default": "likes" }, "sortDirection": { "title": "Sort direction", "enum": [ "desc", "asc" ], "type": "string", "description": "Descending returns highest or newest values first.", "default": "desc" }, "modifiedAfter": { "title": "Modified on or after", "type": "string", "description": "Inclusive ISO date or date-time, e.g. 2024-01-01 or 2024-01-01T00:00:00Z. Date-only values use UTC." }, "minDownloads": { "title": "Minimum downloads", "minimum": 0, "maximum": 1000000000000000, "type": "integer", "description": "Inclusive minimum published download count. A positive value excludes Spaces and repositories without a download count.", "default": 0 }, "minLikes": { "title": "Minimum likes", "minimum": 0, "maximum": 1000000000000000, "type": "integer", "description": "Inclusive minimum number of likes; a positive value excludes repositories without a published count.", "default": 0 }, "maxItems": { "title": "Maximum output rows", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Global cap across all types, including uncharged error rows.", "default": 100 }, "maxPagesPerType": { "title": "Maximum pages per type", "minimum": 1, "maximum": 100, "type": "integer", "description": "Bounded scan budget; restrictive filters may return fewer than maxItems. A warning is logged when the scan limit is reached.", "default": 10 }, "pageSize": { "title": "Repositories per page", "minimum": 1, "maximum": 100, "type": "integer", "description": "Requested Hub page size. A smaller page helps spread a mixed search across all selected types.", "default": 50 }, "concurrency": { "title": "Maximum simultaneous requests", "minimum": 1, "maximum": 10, "type": "integer", "description": "Caps simultaneous Hub HTTP requests across selected types.", "default": 3 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 10, "maximum": 120, "type": "integer", "description": "Time limit per HTTP request. Temporary failures have at most four attempts with backoff.", "default": 30 } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Hugging Face Models & Datasets Search from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: