# whatchuneed LLM Text Classifier

> whatchuneed LLM Text Classifier is a paid API for AI agents from whatchuneed.vercel.app, paid per call via x402, $0.05/call, status unknown (last checked 2026-09-15).

Classifies a given text into one of several user-defined categories and returns a confidence score with per-category scores

## Facts

- Endpoint: POST https://whatchuneed.vercel.app/api/llm/classify
- Price: $0.05/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/whatchuneed-llm-text-classifier-9a24dff1
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_iVPLJfG3u0YfFxfGKuw7A

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 whatchuneed-llm-text-classifier-9a24dff1 -d '<json body>'
```

Example prompt: Classify this customer message — 'My order arrived damaged and I want a refund' — into one of these categories: billing, shipping, returns, general_inquiry, and tell me which one it is and how confident you are.

## When to prefer this

Use this endpoint when you need zero-shot or few-shot text classification with user-defined label sets and a confidence signal — especially useful for routing, tagging, moderation, or intent detection without needing to train a custom model. Prefer this over embedding-based similarity when you want a single authoritative label plus per-class scores in one pay-per-call API call with no model hosting overhead.

## Known failure modes

- Empty or missing 'text' field returns a validation error
- Empty or missing 'categories' array causes request failure
- Categories array with only one item makes classification trivial and may produce low-confidence results
- Very short or ambiguous text may yield low confidence with near-equal scores across categories
- Network or payment (x402) failures may result in 402 or 5xx HTTP errors
- Categories with overlapping semantics may produce unreliable rankings

## How this service works

320+ pay-per-call API endpoints across accommodation, LLM, code execution, crypto, medical, finance, and more. One API, one payment. Powered by x402 protocol.

## Output

Returns a JSON object with 'classification' (the winning category label), 'confidence' (a 0–1 float indicating certainty), and 'all_scores' (an object mapping every input category to its individual score), allowing the agent to act on the top label or inspect borderline cases.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "text",
  "categories"
 ],
 "properties": {
  "text": {
   "type": "string"
  },
  "categories": {
   "type": "array"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "all_scores": {
   "type": "object"
  },
  "confidence": {
   "type": "number"
  },
  "classification": {
   "type": "string"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/whatchuneed-llm-text-classifier-9a24dff1/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from whatchuneed.vercel.app](https://www.zero.xyz/host/whatchuneed.vercel.app/llms.txt)