# AI Text Classifier (Custom Labels + Confidence)

> AI Text Classifier (Custom Labels + Confidence) is a paid API for AI agents from x402-seller-0ay3.onrender.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-14).

Classifies any text into one of your own custom labels with a confidence score, powered by Claude Haiku 4.5

## Facts

- Endpoint: POST https://x402-seller-0ay3.onrender.com/api/ai/classify
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/ai-text-classifier-custom-labels-confidence-7b7321bf
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_wRFp-UISVRSOUeXUhtr_3

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 ai-text-classifier-custom-labels-confidence-7b7321bf -d '<json body>'
```

Example prompt: Classify this customer review using the labels 'positive', 'negative', and 'neutral', and tell me how confident you are: 'The onboarding was smooth but the billing support took forever to respond.'

## When to prefer this

Choose this endpoint when you need fast, cheap, zero-setup text classification into your own arbitrary label set without training a custom model. Ideal for ad-hoc labeling tasks, dynamic label sets, or when you want LLM-quality understanding (nuance, sarcasm, context) rather than a simple keyword or regex approach. At $0.01/call it's cost-effective for moderate volumes. Prefer it over general-purpose LLM calls when you want a structured {label, confidence} response guaranteed every time.

## Known failure modes

- Text exceeds 8000 characters — request rejected
- Fewer than 2 or more than 20 labels provided — validation error
- Empty text or empty label array — bad request
- Service temporarily unavailable on cold start (Render.com free tier spin-up delay)
- Model returns ambiguous classification when text is highly mixed or short

## How this service works

Text classification (sentiment analysis, topic tagging, intent detection, moderation labels...) into one of your own labels, with a confidence score, via Claude Haiku 4.5. JSON body: {text: string (max 8000 chars), labels: string[] (2 to 20 labels)}.

## Output

A JSON object with two fields: `label` (one of the labels you provided) and `confidence` (a float between 0 and 1 indicating how certain the model is). Example: {"label": "negative", "confidence": 0.94}

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "Text to classify (max 8000 chars)."
  },
  "labels": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "description": "List of possible labels (2 to 20)."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "label": "negative",
  "confidence": 0.94
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/ai-text-classifier-custom-labels-confidence-7b7321bf/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402-seller-0ay3.onrender.com](https://www.zero.xyz/host/x402-seller-0ay3.onrender.com/llms.txt)