Hugging Face model API

One Hugging Face model repository: task, library, license, file count, downloads and likes.

Ask your agent

“Call huggingface/model with id meta-llama/Llama-3.1-8B and summarize what comes back.”

Works in any MCP client connected to https://data.openkrill.app/mcp. Install in one line.

Path: huggingface/model
MCP tool: call_endpoint
Credits: 1
Cache: 15 min

Parameters

idstring, required	Repository id such as meta-llama/Llama-3.1-8B

Response

data.resources[] uses the same keys as every other platform: author, engagement, metadata, with Hugging Face-only fields under extras. A failed upstream call is never billed.

More Hugging Face tools

MCP tool call

{
  "name": "call_endpoint",
  "arguments": {
    "path": "huggingface/model",
    "params": {
      "id": "meta-llama/Llama-3.1-8B"
    }
  }
}

curl

curl "https://data.openkrill.app/v1/huggingface/model?id=meta-llama%2FLlama-3.1-8B" \
  -H "x-api-key: YOUR_API_KEY"

Response

{
  "success": true,
  "platform": "huggingface",
  "endpoint": "huggingface/model",
  "data": {
    "resources": [
      { "id": …, "title": …, "text": …, "url": …,
        "author": {…}, "engagement": {…},
        "metadata": {…}, "extras": {…} }
    ]
  },
  "credits_used": 1,
  "cached": false
}