{ "openapi": "3.0.1", "info": { "title": "Hugging Face Hub: Models and Datasets With Download Counts", "description": "Public Hugging Face Hub repositories as rows: model or dataset id, owner, task tag, library, licence, languages, 30-day and all-time downloads, likes, trending score, gated status, parameter count and commit dates. Filter by task, licence, owner, size or update window; sort as you need.", "version": "0.1", "x-build-id": "6CeFdeOmmCQBTdYWg" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/yadroo~huggingface-hub-models/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-yadroo-huggingface-hub-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/yadroo~huggingface-hub-models/runs": { "post": { "operationId": "runs-sync-yadroo-huggingface-hub-models", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/yadroo~huggingface-hub-models/run-sync": { "post": { "operationId": "run-sync-yadroo-huggingface-hub-models", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "repoType": { "title": "Repositories to list", "enum": [ "models", "datasets" ], "type": "string", "description": "One run reads one kind of repository. `models` uses the Hub's model index (task tag, library, parameter count); `datasets` uses the dataset index (task categories, size band, stored bytes, a short card description). The two indexes answer with different fields and different tag spellings, so run the actor twice, or keep two tasks, when you need both. Every row names its own kind in `repoType`.", "default": "models" }, "search": { "title": "Keyword", "type": "string", "description": "Free-text term handed to the Hub's own search, which matches it against the repository id and owner (`qwen`, `whisper`, `embedding`, `medical`). It travels exactly as you type it - the Hub decides what matches, so a partial word works and no correction is applied here. Leave it empty to list everything the filters allow, in the order you chose." }, "repoIds": { "title": "Exact repository ids", "maxItems": 50, "type": "array", "description": "Look up named repositories instead of searching: one `owner/name` per line (`Qwen/Qwen3-0.6B`, `openai/gpt-oss-20b`, `cais/mmlu` for datasets). Case and surrounding spaces are ignored and a full Hub URL is reduced to the id. Each id is read from its own metadata endpoint, so these rows carry the detail columns even with the detail switch off. An id the Hub does not serve anonymously - deleted, renamed, private or misspelt - comes back as one row with `found: false`, because the Hub answers 401 for every repository it will not show and those cases cannot be told apart from outside. The filters below still apply to the rows.", "items": { "type": "string" } }, "pipelineTag": { "title": "Task (models only)", "type": "string", "description": "Keep only models whose owner declared this task. Pick a value from the list or type another one: the Hub published 59 task ids on 2026-10-21 and keeps adding them, so this field accepts any of them. Case, spaces and the usual separators are read the same (`text to image`, `Text-To-Image`). A value that is not a Hub task id stops the run and names the closest ids instead of returning a wider list. Ignored for datasets - those use the task-categories field." }, "library": { "title": "Library or weight format", "type": "string", "description": "Keep only repositories carrying this library or weight format - the short answer to \"what can my stack actually load\": `gguf` for llama.cpp-style local builds, `transformers` for the Python pipeline, `diffusers` for image models, `mlx` for Apple silicon, `onnx` or `openvino` for runtime exports. It is sent as a Hub tag, which matches exactly, and it is checked against the vocabulary of the kind you chose - the dataset index has its own short list (`datasets`, `pandas`, `polars`, `mlcroissant`, `webdataset` and a few more), the model index a long one. Case and spaces are ignored; a value neither index knows stops the run with the closest ids named." }, "licenses": { "title": "Licences", "maxItems": 5, "type": "array", "description": "Keep only repositories published under one of these licence ids, one per line as the Hub writes them: `apache-2.0`, `mit`, `cc-by-4.0`, `cc-by-nc-4.0`, `cc-by-sa-4.0`, `openrail`, `gemma`, `llama3.1`, `llama3.3`, `odc-by`, `other`. The `license:` prefix may be written or left out. Each licence is asked for in its own request and the answers are merged, so five licences cost five requests per page. An id the Hub does not know stops the run with the closest ones named; the README lists the frequent ones.", "items": { "type": "string" } }, "languages": { "title": "Languages", "maxItems": 5, "type": "array", "description": "Keep only repositories whose owner declared one of these languages, one code per line (`en`, `ru`, `kk`, `de`, `zh`, `multilingual`). The Hub carries thousands of language tags - more than 5,000 on models alone - so codes are lower-cased and passed through unchanged with no correction and no suggestions; a code nothing carries simply yields no rows and the run status says which filter matched nothing. Models and datasets spell the language tag differently and the actor sends the right form for the kind you chose. Many repositories declare no language at all and are invisible to this filter, so leave it empty when coverage matters more than precision.", "items": { "type": "string" } }, "taskCategories": { "title": "Task categories (datasets only)", "maxItems": 5, "type": "array", "description": "Keep only datasets tagged with one of these task categories, one per line (`question-answering`, `text-generation`, `text-classification`, `summarization`, `automatic-speech-recognition`, `image-classification`, `translation`, `table-question-answering`). They share the vocabulary of the model tasks. One request per value, merged like the licences. Ignored for models.", "items": { "type": "string" } }, "tagFilters": { "title": "Extra Hub tags (advanced)", "maxItems": 10, "type": "array", "description": "Raw Hub tag filters, one per line, all of which a repository must carry - the escape hatch for filters this input does not name. Examples: `size_categories:1K