Hugging Face Model Search

huggingfacehub/search-models

Searches Hugging Face Hub models and returns up to `limit` (1 to 25, default 10) of them ordered by `sort` (downloads, likes, createdAt, lastModified or trendingScore; default downloads, most first): id, author, likes, downloads over the last 30 days, task (`pipeline_tag`), library, dates and up to 40 tags. At least one of `search` (words in the model id), `filter` (a tag such as text-classification or license:apache-2.0) or `author` is required. There is no paging. Each repo has its own licence, set by its authors; it appears in `cardData.license` and in the `license:` tag where they set it. Hugging Face Hub metadata, served by Eden Engine; not an official Hugging Face product.

activeper callv1

Price

$0.0026 per call

You pay the price shown. If a call turns out to cost more than its quote, you pay the actual price, capped at twice the quote. No monthly minimum. Top-ups start at $0.50.

Data source

Hugging Face

Data from the Hugging Face Hub (https://huggingface.co). Each model and dataset carries its own licence, set by its authors on the repo card. Served by Eden Engine; not an official Hugging Face product.

Use it

Five steps: search, inspect, learn, run, settle. No per-tool setup; your agent reaches this tool through the meta-tools it already has.

Connect once and your AI can find and run this tool, and any other it needs.

Install it Create an account

agent

// 1. search: find the tool
omnial_search({ query: "what you need" })

// 2. inspect: price and input schema
omnial_inspect({ tool: "huggingfacehub/search-models" })

// 3. learn: read the usage guide at runtime
omnial_learn({ tool: "huggingfacehub/search-models" })

// 4. run: price the exact call first, then run it
omnial_execute({ tool: "huggingfacehub/search-models", input: { /* see input_schema */ }, dry_run: true })
omnial_execute({ tool: "huggingfacehub/search-models", input: { /* ... */ } })

// 5. settle: the call is charged when it finishes, nothing to do

Not connected yet? Point your MCP client at https://mcp.eden-engine.com/mcp, then copy a config for your client.

Pricing

Every charge this tool can incur.

Charge	Price
Per call	$0.0026

Updated: Oct 25, 2026

Input and output schemas

Input schema

input_schema.json

{
  "type": "object",
  "anyOf": [
    {
      "required": [
        "search"
      ]
    },
    {
      "required": [
        "filter"
      ]
    },
    {
      "required": [
        "author"
      ]
    }
  ],
  "properties": {
    "sort": {
      "enum": [
        "downloads",
        "likes",
        "createdAt",
        "lastModified",
        "trendingScore"
      ],
      "type": "string",
      "default": "downloads",
      "description": "Order, most first. Default downloads."
    },
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 25,
      "minimum": 1,
      "description": "Most results, 1 to 25. Default 10."
    },
    "author": {
      "type": "string",
      "pattern": "^[A-Za-z0-9][A-Za-z0-9._-]{0,95}$",
      "description": "Owner (user or organisation) whose repos to list, for example google."
    },
    "filter": {
      "type": "string",
      "pattern": "^[A-Za-z0-9][A-Za-z0-9:._-]{0,79}$",
      "description": "One tag to require, for example text-classification, safetensors or license:apache-2.0."
    },
    "search": {
      "type": "string",
      "pattern": "^[A-Za-z0-9][A-Za-z0-9 ._:/+-]{0,79}$",
      "description": "Words to look for in model ids, for example bert or llama. Letters, digits, spaces and . _ : / + - only, up to 80 characters."
    }
  },
  "additionalProperties": false
}

Output schema

output_schema.json

{
  "type": "object",
  "required": [
    "count",
    "results"
  ],
  "properties": {
    "count": {
      "type": "integer",
      "description": "Items in `results`."
    },
    "clipped": {
      "type": "boolean",
      "description": "True when the hook shortened a string, list or object; strings end with a note giving the count dropped."
    },
    "results": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "id"
        ],
        "properties": {
          "id": {
            "type": "string",
            "description": "Repo id, owner/name."
          },
          "tags": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "At most 40 tags (library, task, language, licence:..., dataset:... and so on)."
          },
          "gated": {
            "type": [
              "boolean",
              "string"
            ],
            "description": "false for an open repo, or \"auto\" / \"manual\" when access needs a request."
          },
          "likes": {
            "type": "integer"
          },
          "author": {
            "type": "string"
          },
          "private": {
            "type": "boolean"
          },
          "createdAt": {
            "type": "string"
          },
          "downloads": {
            "type": "integer",
            "description": "Downloads in the last 30 days."
          },
          "description": {
            "type": [
              "string",
              "null"
            ],
            "description": "Dataset card summary, clipped to 500 characters; datasets only."
          },
          "lastModified": {
            "type": "string"
          },
          "library_name": {
            "type": [
              "string",
              "null"
            ]
          },
          "pipeline_tag": {
            "type": [
              "string",
              "null"
            ],
            "description": "Task, for example text-classification; absent or null when the authors set none."
          },
          "trendingScore": {
            "type": "number"
          }
        },
        "additionalProperties": true
      }
    }
  },
  "description": "The Hub's model list, reduced by the hook (see `clipped`).",
  "additionalProperties": true
}