You can access the Hugging Face Models and Datasets 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.

Python

JavaScript

CLI

OpenAPI

HTTP

MCP

{
  "openapi": "3.0.1",
  "info": {
    "version": "0.0",
    "x-build-id": "sRktNNEHQPlviZoxS"
  },
  "servers": [
    {
      "url": "https://api.apify.com/v2"
    }
  ],
  "paths": {
    "/acts/apt_marble~hugging-face-models-and-datasets-scraper/run-sync-get-dataset-items": {
      "post": {
        "operationId": "run-sync-get-dataset-items-apt_marble-hugging-face-models-and-datasets-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": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    },
    "/acts/apt_marble~hugging-face-models-and-datasets-scraper/runs": {
      "post": {
        "operationId": "runs-sync-apt_marble-hugging-face-models-and-datasets-scraper",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor and returns information about the initiated run in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$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": {
                  "$ref": "#/components/schemas/runsResponseSchema"
                }
              }
            }
          }
        }
      }
    },
    "/acts/apt_marble~hugging-face-models-and-datasets-scraper/run-sync": {
      "post": {
        "operationId": "run-sync-apt_marble-hugging-face-models-and-datasets-scraper",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$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": {
          "kind": {
            "title": "Search for",
            "enum": [
              "models",
              "datasets"
            ],
            "type": "string",
            "description": "Models or datasets.",
            "default": "models"
          },
          "query": {
            "title": "Search query",
            "type": "string",
            "description": "Keyword (optional).",
            "default": "sentiment"
          },
          "filter": {
            "title": "Tag filter",
            "type": "string",
            "description": "Optional tag such as text-classification, pytorch or en."
          },
          "sort": {
            "title": "Sort by",
            "enum": [
              "downloads",
              "likes",
              "trendingScore",
              "createdAt",
              "lastModified"
            ],
            "type": "string",
            "description": "Order of results.",
            "default": "downloads"
          },
          "maxItems": {
            "title": "Maximum results",
            "minimum": 1,
            "maximum": 5000,
            "type": "integer",
            "description": "Stop after this many results.",
            "default": 100
          }
        }
      },
      "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
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}

Hugging Face Models and Datasets Scraper OpenAPI definition

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 and Datasets Scraper from the options below:

OpenAPI.json

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:

Hugging Face Models and Datasets Scraper API in Python

Hugging Face Models and Datasets Scraper API in JavaScript

Hugging Face Models and Datasets Scraper API through CLI

Hugging Face Models and Datasets Scraper API

Telegram Comments Scraper

apt_marble/telegram-comments-scraper

Get every public comment under any Telegram post: author name, @handle, text, timestamp, reactions, photos and the comment each one answers — one row each, ready for CSV, Excel or JSON. Point it at a list of posts or a whole channel. No Telegram account, phone number or login needed.

Hamza

Hugging Face Model Scraper

parseforge/hugging-face-model-scraper

Scrapes Hugging Face model cards by task, library, license, language, or keyword search. Returns each model as a flat row with downloads, likes, author, tags, and last-modified date.

ParseForge

5.0

(3)

Hugging Face Image AI

alizarin_refrigerator-owner/hugging-face-image-ai

Image processing w/Hugging Face models Text-to-Image: Stable Diffusion, SDXL, DALL-E generation Image-to-Image: Transform images Inpainting: Edit parts of images Classification: Identify objects Object Detection: Locate label objects Segmentation: Pixel analysis Captioning: Generate descriptions

The Howlers

AI Face Generator

easyapi/ai-face-generator

Effortlessly creates, processes, and stores diverse HD facial images. Perfect for designers, developers, researchers, and creatives needing unique, royalty-free face images for projects, datasets, or artistic inspiration. 🤖🎨🚀

EasyApi

5.0

(1)

Hugging Face Datasets Scraper

parseforge/hugging-face-datasets-scraper

Scrape Hugging Face dataset metadata by search query, task category, language, and license. Returns name, description, tags, downloads, likes, and trending score. No API key needed.

ParseForge

Huggingface Models

david_flagg/huggingface-models

Scrape model metadata from HuggingFace Hub — the largest open-source ML model registry. Get downloads, likes, trending scores, licenses, tags, and architecture info for 1M+ models. Filter by task type, ML library, or author. Uses the official HF API — no auth required.

David Flagg

Yandex Images Scraper

apt_marble/yandex-images-scraper

Search Yandex Images and get every result as a clean row: full-size picture address, pixel size, file size, thumbnail, title and the page it appears on. Filter by size, shape and picture type. Around 1,200 different pictures per search term, with repeats reported once.

Hamza

OpenRouter AI Model Pricing Scraper

parseforge/openrouter-models-pricing-scraper

Scrapes the OpenRouter model catalog and returns each model as a flat row with prompt price, completion price, context length, modality, and provider. Filter by provider, modality, price ceiling, and context window.

ParseForge

Hugging Face Models Scraper - AI Model Intelligence

thirdwatch/hugging-face-models-scraper

Search public Hugging Face models and export downloads, likes, task, library, license, tags, files, gated status, hashes, timestamps, authors, and canonical model URLs. Built for research and data pipelines. No login, cookies, or API keys — clean JSON output and pay-per-result pricing.

Thirdwatch

LLM Dataset Processor

dusan.vystrcil/llm-dataset-processor

Allows you to process output of other actors or stored dataset with single LLM prompt. It's useful if you need to enrich data, summarize content, extract specific information, or manipulate data in a structured way using AI.