# Hugging Face Model Search

> Hugging Face Model Search is a paid API for AI agents from the-stall.intuitek.ai, paid per call via x402, $0.002/call, status unknown (last checked 2026-09-14).

Searches Hugging Face Hub for AI models by keyword, architecture, or task type, returning ranked results sorted by downloads, likes, or recency

## Facts

- Endpoint: GET https://the-stall.intuitek.ai/cap/hf-model-search
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/hugging-face-model-search-c24ba5fa
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_qBIdcwb4sBd6wrBXsDE0e

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability hugging-face-model-search-c24ba5fa
```

Example prompt: Search Hugging Face for the top 10 most-downloaded text-generation models matching 'llama' and sort the results by downloads.

## When to prefer this

Use this endpoint when an agent needs to discover, compare, or recommend AI models from Hugging Face Hub by name, architecture, or task. Ideal for model selection workflows, research tasks, or when a user wants to find the best open-source model for a specific ML pipeline task without needing a Hugging Face account or API key.

## Known failure modes

- Empty results if query is too specific or misspelled — returns empty array
- Invalid task filter value returns error or empty results
- Limit out of range (less than 1 or more than 20) causes validation error
- Hugging Face Hub API unavailability causes upstream timeout or 503
- Invalid sort enum value causes request rejection

## How this service works

Search HuggingFace Hub for ML models. Specify a keyword (e.g. 'bert', 'llama', 'stable diffusion') and optional task filter (e.g. 'text-classification', 'text-generation', 'image-classification'). Returns top results sorted by downloads or likes, including model ID, author, pipeline task, framework library, download count, likes count, and tags.

## Output

A ranked list of up to 20 Hugging Face models matching the query, including model names, task types, download counts, like counts, and last modified dates, sorted by the specified criterion (downloads, likes, or lastModified).

## Example request

```json
{
 "input": {
  "type": "http",
  "method": "GET",
  "queryParams": {
   "sort": "downloads",
   "task": "text-classification",
   "limit": 10,
   "query": "bert"
  }
 }
}
```

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "required": {
   "type": "string"
  },
  "properties": {
   "type": "string"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/hugging-face-model-search-c24ba5fa/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from the-stall.intuitek.ai](https://www.zero.xyz/host/the-stall.intuitek.ai/llms.txt)