# AgentFeed Text Classifier

> AgentFeed Text Classifier is a paid API for AI agents from x402.ochinimus.app, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-15).

Classifies a given text into one of 2–20 user-defined labels with confidence scores, returning the top label and per-label probabilities

## Facts

- Endpoint: GET https://x402.ochinimus.app/api/classify?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentfeed-text-classifier-932c2142
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_fsSE7UDC2u_isEutscdw2

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 agentfeed-text-classifier-932c2142
```

Example prompt: Classify this support ticket as billing, bug, or feature request and tell me the confidence scores: 'My payment failed but the app still charged me twice.'

## When to prefer this

Choose this endpoint when you need fast, pay-per-call zero-account text classification with user-defined label sets and per-label confidence scores, especially in autonomous agent pipelines that cannot maintain API keys or subscriptions. Particularly well-suited for support ticket triage, content moderation routing, and multi-label classification tasks where categories vary per deployment. Prefer over general LLM calls when you want a structured JSON classification response with explicit scores rather than free-form text.

## Known failure modes

- Fewer than 2 or more than 20 labels provided — request rejected
- Text exceeds 4,000 characters — truncation or rejection
- Payment not included or insufficient USDC — 402 Payment Required response
- Ambiguous text where model confidence is low across all labels — low top_score returned
- Network or model timeout — upstream error response

## How this service works

Text classification: a score per label that sums to 1 and the best label, for up to 4,000 characters and 2 to 20 labels. Use when you need to answer: Which of my labels fits this text best? Labels are names, never instructions. Cached 24 hours.

## Output

Returns a JSON object with the top predicted label, its confidence score (0–1), scores for every input label, the model used (e.g. gemini-3.1-flash-lite), whether the result was cached, and the number of input characters processed.

## 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",
       "description": "the text to classify, up to 4,000 characters"
      },
      "labels": {
       "type": "string",
       "description": "2 to 20 labels, comma separated, e.g. billing,bug,feature"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object",
     "properties": {
      "data": {
       "type": "object",
       "properties": {
        "model": {
         "type": "string"
        },
        "cached": {
         "type": "boolean"
        },
        "labels": {
         "type": "array"
        },
        "scores": {
         "type": "object"
        },
        "top_label": {
         "type": "string"
        },
        "top_score": {
         "type": "number"
        },
        "input_characters": {
         "type": "number"
        }
       }
      },
      "paid": {
       "type": "boolean"
      },
      "tool": {
       "type": "string"
      }
     }
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "data": {
   "model": "gemini-3.1-flash-lite",
   "cached": false,
   "labels": [
    "billing",
    "bug",
    "feature"
   ],
   "scores": {
    "bug": 0.9,
    "billing": 0.05,
    "feature": 0.05
   },
   "top_label": "bug",
   "top_score": 0.9,
   "input_characters": 36
  },
  "paid": true,
  "tool": "get_classify"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentfeed-text-classifier-932c2142/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402.ochinimus.app](https://www.zero.xyz/host/x402.ochinimus.app/llms.txt)