{
"openapi": "3.0.1",
"info": {
"title": "Hugging Face Scraper",
"description": "Scrape Hugging Face models, datasets, Spaces & papers: downloads, likes, parameters, license, tasks, inference providers and model cards. Search or paste any URL.",
"version": "1.0",
"x-build-id": "M1bsg2Fdjr7pXNGZJ"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/dtrungtin~huggingface-scraper/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-dtrungtin-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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/dtrungtin~huggingface-scraper/runs": {
"post": {
"operationId": "runs-sync-dtrungtin-huggingface-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/dtrungtin~huggingface-scraper/run-sync": {
"post": {
"operationId": "run-sync-dtrungtin-huggingface-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"resourceType": {
"title": "What to scrape",
"enum": [
"models",
"datasets",
"spaces",
"papers"
],
"type": "string",
"description": "Which part of the Hugging Face Hub to search. Ignored when you provide URLs below.",
"default": "models"
},
"searchTerms": {
"title": "Search terms",
"type": "array",
"description": "Full-text search, e.g. llama, whisper or sentiment. Each term is scraped separately. Leave empty to browse everything that matches the filters. For papers, searches titles and abstracts; leave empty for the Daily Papers feed.",
"items": {
"type": "string"
}
},
"sort": {
"title": "Sort by",
"enum": [
"trending",
"downloads",
"likes",
"created",
"modified"
],
"type": "string",
"description": "Order of results. Spaces cannot be sorted by downloads. Papers support Trending; any other value lists the newest papers.",
"default": "trending"
},
"maxItems": {
"title": "Max results per search or URL",
"minimum": 0,
"type": "integer",
"description": "Maximum number of results saved for each search term or URL. Set to 0 for no limit (a full crawl of all models is over 2 million results).",
"default": 100
},
"startUrls": {
"title": "Hugging Face URLs",
"type": "array",
"description": "Optional. Paste any huggingface.co URL and its data is scraped instead of the search above. Supported: listing pages with filters (e.g. https://huggingface.co/models?pipeline_tag=text-generation&sort=trending), model / dataset / Space pages, user or organization profiles, collections, and papers pages (daily, trending, a date, or a single paper).",
"items": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"title": "URL of a web page",
"format": "uri"
}
}
}
},
"author": {
"title": "Author or organization",
"type": "string",
"description": "Only results published by this user or organization, e.g. meta-llama, google, Qwen."
},
"task": {
"title": "Task",
"enum": [
"any-to-any",
"audio-classification",
"audio-text-to-text",
"audio-to-audio",
"automatic-speech-recognition",
"depth-estimation",
"document-question-answering",
"feature-extraction",
"fill-mask",
"image-classification",
"image-feature-extraction",
"image-segmentation",
"image-text-to-image",
"image-text-to-text",
"image-text-to-video",
"image-to-3d",
"image-to-image",
"image-to-text",
"image-to-video",
"keypoint-detection",
"mask-generation",
"object-detection",
"question-answering",
"reinforcement-learning",
"sentence-similarity",
"summarization",
"table-question-answering",
"tabular-classification",
"tabular-regression",
"text-classification",
"text-generation",
"text-ranking",
"text-to-3d",
"text-to-image",
"text-to-speech",
"text-to-video",
"token-classification",
"translation",
"unconditional-image-generation",
"video-classification",
"video-text-to-text",
"video-to-video",
"visual-document-retrieval",
"visual-question-answering",
"zero-shot-classification",
"zero-shot-image-classification",
"zero-shot-object-detection"
],
"type": "string",
"description": "Models: pipeline task. Datasets: task category. Not available for Spaces."
},
"library": {
"title": "Library",
"type": "string",
"description": "Models: e.g. transformers, gguf, diffusers, mlx, onnx. Datasets: e.g. datasets, pandas, polars."
},
"language": {
"title": "Language",
"type": "string",
"description": "ISO language code, e.g. en, vi, fr, zh."
},
"license": {
"title": "License",
"type": "string",
"description": "License id, e.g. apache-2.0, mit, cc-by-4.0, llama3.1."
},
"tags": {
"title": "Tags",
"type": "array",
"description": "Any Hugging Face tags that results must have, e.g. conversational, base_model:finetune:Qwen/Qwen3-8B, size_categories:1K<n<10K, mcp-server.",
"items": {
"type": "string"
}
},
"minParameters": {
"title": "Min parameters (models)",
"pattern": "^(\\d+(\\.\\d+)?\\s*[KMBTkmbt]?)?$",
"type": "string",
"description": "Minimum model size, e.g. 500M, 7B."
},
"maxParameters": {
"title": "Max parameters (models)",
"pattern": "^(\\d+(\\.\\d+)?\\s*[KMBTkmbt]?)?$",
"type": "string",
"description": "Maximum model size, e.g. 3B, 70B."
},
"spaceSdk": {
"title": "Space SDK",
"enum": [
"gradio",
"streamlit",
"docker",
"static"
],
"type": "string",
"description": "Only Spaces built with this SDK."
},
"papersDate": {
"title": "Papers date",
"pattern": "^(\\d{4}-\\d{2}-\\d{2}|\\d{4}-W\\d{2}|\\d{4}-\\d{2})?$",
"type": "string",
"description": "Daily Papers for a day (2026-09-22), ISO week (2026-W38) or month (2026-09). Leave empty for the latest papers."
},
"minDownloads": {
"title": "Min downloads (last 30 days)",
"minimum": 0,
"type": "integer",
"description": "Skip results with fewer downloads. Fastest when sorting by Most downloads."
},
"minLikes": {
"title": "Min likes / upvotes",
"minimum": 0,
"type": "integer",
"description": "Skip results with fewer likes (upvotes for papers). Fastest when sorting by Most likes."
},
"createdAfter": {
"title": "Created after",
"type": "string",
"description": "Only results created (papers: published) after this date. Also accepts a relative period such as 7 days, which is useful for scheduled monitoring runs. Fastest when sorting by Recently created."
},
"includeReadme": {
"title": "Include README / model card text",
"type": "boolean",
"description": "Adds the full README (model card, dataset card or Space description) as Markdown. Great for LLM/RAG pipelines. Makes runs slower (one extra request per result).",
"default": false
},
"includeFiles": {
"title": "Include file list",
"type": "boolean",
"description": "Adds the list of files in each repository (weights, configs, notebooks...). For datasets this needs one extra request per result.",
"default": false
},
"includeCardData": {
"title": "Include raw card metadata",
"type": "boolean",
"description": "Adds the raw YAML metadata of the model/dataset card (base model, datasets, metrics, widget examples...). Can be large.",
"default": false
},
"hfToken": {
"title": "Hugging Face access token",
"type": "string",
"description": "Optional. A free read token gives you a higher rate limit and access to your own private or gated repos. Stored encrypted."
},
"proxyConfiguration": {
"title": "Proxy configuration",
"type": "object",
"description": "Not needed in most cases: the Hugging Face API is public. Enable only if you hit rate limits on very large runs without a token.",
"default": {
"useApifyProxy": false
}
}
}
},
"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
}
}
}
}
}
}
}
}
}
}