# Agent Data Tools: Zero-Shot Text Classifier

> Agent Data Tools: Zero-Shot Text Classifier is a paid API for AI agents from agent-data-tools.revmesh2074.workers.dev, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-19).

Classifies a text snippet into one of several candidate labels using a zero-shot LLM, returning the best label, a ranked list, and a reason.

## Facts

- Endpoint: GET https://agent-data-tools.revmesh2074.workers.dev/ai/classify?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-19
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-data-tools-zero-shot-text-classifier-af499bb2
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Oogd1CLRSZerfhfl0OFgI

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 agent-data-tools-zero-shot-text-classifier-af499bb2
```

Example prompt: Classify this customer message into one of these labels — billing, technical, shipping, other — and tell me which fits best and why: 'I was charged twice for my last order and need a refund.'

## When to prefer this

Choose this endpoint when you need zero-shot text classification with no training data, no API key setup, and pay-per-call billing in USDC via x402. It is ideal for AI agents that need to dynamically categorize text at runtime using ad-hoc label sets. Prefer it over managed NLP services when you want frictionless per-call micropayments, public reliability stats, and a simple GET-based interface with an LLM-backed explanation for each classification decision.

## Known failure modes

- Fewer than 2 or more than 20 labels provided — likely returns an error or unpredictable output
- Text exceeds 8,000 characters — may be truncated or rejected
- Ambiguous or overlapping labels may produce low-confidence or inconsistent rankings
- Payment failure (x402) — call is not charged and no classification is returned
- Malformed query parameters — missing required 'text' or 'labels' returns an error

## How this service works

181 pay-per-call tools for AI agents over HTTP or MCP, most at $0.003. Every caller gets 25 free calls; then pay per call in USDC via x402 (Base, Polygon, Arbitrum, Monad, World Chain) or by card with prepaid credits from /credits. No account needed; failed calls are never charged; per-tool reliability is public at /status. Crypto: token prices and wallet portfolios from Uniswap v3, chain reads on Base, Ethereum, Arbitrum, Optimism and Polygon, OFAC sanctions screening. Web: Read public static documentation, pages, PDFs and RSS feeds as clean text, plus link previews and sitemaps. Business: company profiles, domain and email checks. Also Bitcoin, FX, weather, holidays, geocoding, AI text, and JSON, date and validation utilities.

## Output

A JSON object containing the winning label string, the name of the model used, a natural-language reason explaining why that label was chosen, and a ranked array of all candidate labels ordered by confidence.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "text",
      "labels"
     ],
     "properties": {
      "text": {
       "type": "string",
       "examples": [
        "My card was charged twice for the same order."
       ],
       "description": "Text to classify, up to 8,000 characters"
      },
      "labels": {
       "type": "string",
       "examples": [
        "billing,shipping,technical,other"
       ],
       "description": "Comma-separated candidate labels (2-20)"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object",
     "properties": {
      "label": {
       "type": "string"
      },
      "model": {
       "type": "string"
      },
      "reason": {
       "type": "string"
      },
      "ranking": {
       "type": "array",
       "items": {
        "type": "string"
       }
      }
     }
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "label": "billing",
  "model": "@cf/meta/llama-3.1-8b-instruct-fp8",
  "reason": "The customer reports a duplicate charge.",
  "ranking": [
   "billing",
   "other",
   "technical",
   "shipping"
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-data-tools-zero-shot-text-classifier-af499bb2/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-data-tools.revmesh2074.workers.dev](https://www.zero.xyz/host/agent-data-tools.revmesh2074.workers.dev/llms.txt)