# Tokenguard /dev/models Endpoint

> Tokenguard /dev/models Endpoint is a paid API for AI agents from eltociear-tokenguard.hf.space, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-14).

Searches and lists available AI/ML models on Hugging Face by keyword query, returning model IDs, download counts, and pipeline tags

## Facts

- Endpoint: POST https://eltociear-tokenguard.hf.space/dev/models
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/tokenguard-dev-models-endpoint-99c32e53
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_G9TWz4BFre_26mGZ2pjQn

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 tokenguard-dev-models-endpoint-99c32e53 -d '<json body>'
```

Example prompt: Search for available Llama models on Hugging Face and show me the top results including their download counts and pipeline tags.

## When to prefer this

Use this endpoint when an agent needs to discover or search Hugging Face models by keyword, retrieve download statistics, or identify which pipeline tag a model belongs to — particularly useful for model selection workflows or when an agent needs to enumerate available open-source LLMs, embedding models, or other ML models by name.

## Known failure modes

- Empty query returns no results or error
- Query string matches no known models, returning count=0 and empty results array
- Service unavailable on Hugging Face Space (cold start latency or timeout)
- Payment failure via x402 micropayment protocol returns 402 status
- Malformed POST body returns 400 or unstructured error response

## How this service works

Search the Hugging Face Hub for models or datasets (downloads, likes, task, library, tags) or fetch one by id

## Output

A JSON object with a 'kind' field set to 'models', a 'count' of results, the original query string, and a 'results' array where each item contains model ID, number of downloads, and pipeline tag (e.g. text-generation).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "kind": {
   "enum": [
    "models",
    "datasets"
   ],
   "type": "string",
   "description": "Default models"
  },
  "limit": {
   "type": "integer",
   "description": "1-30 results (default 10)"
  },
  "query": {
   "type": "string",
   "description": "Search terms"
  },
  "model_id": {
   "type": "string",
   "description": "Fetch one by id, e.g. meta-llama/Llama-3-8B"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "kind": "models",
  "count": 2,
  "query": "llama",
  "results": [
   {
    "id": "meta-llama/Llama-3-8B",
    "downloads": 1200000,
    "pipeline_tag": "text-generation"
   }
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/tokenguard-dev-models-endpoint-99c32e53/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from eltociear-tokenguard.hf.space](https://www.zero.xyz/host/eltociear-tokenguard.hf.space/llms.txt)