# Vextorium Text Classification

> Vextorium Text Classification is a paid API for AI agents from api.vextorium.com, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-12).

Classifies a piece of text into one or more user-provided candidate labels using a local LLM, returning matched labels, a confidence score, and a reasoning explanation.

## Facts

- Endpoint: POST https://api.vextorium.com/v1/classify-text?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/vextorium-text-classification-2c363c6d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_xeV6z5nICgIcpbbfB56AB

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 vextorium-text-classification-2c363c6d -d '<json body>'
```

Example prompt: Classify this support message into one of these labels — 'complaint', 'refund_request', 'general_inquiry', or 'compliment' — and tell me how confident you are: 'I've been waiting 3 weeks for my order and nobody is responding to my emails.'

## When to prefer this

Choose this endpoint when you need zero-shot text classification with a natural language explanation and confidence score, without needing to train a custom model. Ideal for dynamic label sets defined at call time (e.g. support categories, intent buckets, topic tags). Prefer this over embedding-based classifiers when interpretability (the 'reason' field) matters. The pay-per-call x402 model makes it suitable for sporadic or agent-driven workloads without subscription overhead.

## Known failure modes

- Fewer than 2 or more than 30 candidate labels provided — validation error
- Text field is missing or empty — required field error
- Label array is missing — required field error
- Ambiguous text leads to low confidence score with unexpected label assignment
- Non-English text may reduce accuracy depending on model language support
- Payment failure via x402 results in 402 response before processing

## How this service works

552 pay-per-call data APIs for AI agents: Solana and EVM on-chain data, tokenized stocks, DeFi, Hyperliquid, economy and official statistics, FX, validation, web and developer tools. Pay in USDC via x402.

## Output

Returns a JSON object with the model name used (e.g. 'Qwen3-8B (local)'), an array of matched labels, a natural-language reason explaining why those labels were chosen, and a confidence score between 0 and 1.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "Text to classify"
  },
  "labels": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "description": "2-30 candidate labels"
  },
  "multiple": {
   "type": "boolean",
   "description": "Allow several labels (default false)"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "model": "Qwen3-4B (local)",
  "labels": [
   "reclamacion"
  ],
  "reason": "El texto expresa un problema con una orden y falta de respuesta, lo cual son elementos ...",
  "confidence": 0.95
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/vextorium-text-classification-2c363c6d/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.vextorium.com](https://www.zero.xyz/host/api.vextorium.com/llms.txt)