Hugging Face Models Scraper
Pricing
from $0.30 / 1,000 model records
Hugging Face Models Scraper
Export public Hugging Face model metadata, downloads, likes, tags, licenses and update dates for model research and organization comparisons.
Hugging Face Models Scraper
Pricing
from $0.30 / 1,000 model records
Export public Hugging Face model metadata, downloads, likes, tags, licenses and update dates for model research and organization comparisons.
You can access the Hugging Face Models Scraper programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.1", "x-build-id": "KUql5gC7JQmlVzfU8" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/fetch_cat~hugging-face-models-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-fetch_cat-hugging-face-models-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/fetch_cat~hugging-face-models-scraper/runs": { "post": { "operationId": "runs-sync-fetch_cat-hugging-face-models-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/fetch_cat~hugging-face-models-scraper/run-sync": { "post": { "operationId": "run-sync-fetch_cat-hugging-face-models-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": { "search": { "title": "Search query", "type": "string", "description": "Search the public model catalog by model name or ID, for example llama or bert. Leave empty to browse models using the other supported filters. The form prefill is an example, not an API default." }, "author": { "title": "Author / organization", "type": "string", "description": "Optional Hugging Face namespace such as google, microsoft, meta-llama, openai, or stabilityai. Leave empty to search all authors." }, "sort": { "title": "Sort models by", "enum": [ "downloads", "likes", "trending", "lastModified" ], "type": "string", "description": "Choose descending catalog order before the result limit: most downloads, most likes, highest trending score, or most recently modified. Omitted or unsupported sort values use downloads in the current runtime.", "default": "downloads" }, "limit": { "title": "Maximum models", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Save at most 1–1,000 model records. The form and platform schema default to 20; the runtime uses 50 if it receives no limit. Set an explicit value for repeatable calls. A result or time limit can end collection before all matches are returned.", "default": 20 }, "includeDetails": { "title": "Include detail data", "type": "boolean", "description": "Request extra public metadata for each model, such as structured cardData and repository file counts, when available. This takes longer and does not download files or full card text. If a detail lookup fails, summary data may still be saved with detailFetched=false and a detailError note.", "default": false }, "language": { "title": "Language", "type": "string", "description": "Accepted language parameter, for example en. In the current integration this parameter does not reliably restrict catalog results. Inspect returned tags/languages and filter the exported rows if needed; do not rely on this field for language-only selection." }, "pipelineTag": { "title": "Pipeline tag", "type": "string", "description": "Optional model task such as text-generation, image-classification, sentence-similarity, automatic-speech-recognition, or text-to-image." }, "library": { "title": "Library / framework", "type": "string", "description": "Accepted library parameter, for example transformers. In the current integration this parameter does not reliably restrict catalog results. Inspect returned libraryName and filter the exported rows if needed." }, "license": { "title": "License", "type": "string", "description": "Accepted license parameter, for example apache-2.0. In the current integration this parameter does not reliably restrict catalog results. Inspect returned license/tags and the original model license; do not rely on this field for license-only selection." }, "gated": { "title": "Gated access", "type": "boolean", "description": "Optionally include only gated or only ungated public models." }, "inferenceProvider": { "title": "Inference provider", "type": "string", "description": "Optional inference-provider value sent to the public catalog. Use a valid Hugging Face provider identifier; unsupported values can cause the catalog request to fail. This does not invoke inference or return provider pricing." }, "maxRunSeconds": { "title": "Maximum run time (seconds)", "minimum": 35, "maximum": 270, "type": "integer", "description": "35–270 second collection budget, default 270. Collection reserves time for saving results, so it may stop early and return fewer rows. Completed rows are preserved; this is not a guarantee that every requested model will be collected.", "default": 270 } } }, "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 Scraper 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: