# AgentShelf Text Statistics

> AgentShelf Text Statistics is a paid API for AI agents from agentshelf.syntexa.ch, paid per call via x402, $0.001/call, status unknown (last checked 2026-10-01).

Computes heuristic text statistics (character count, word count, sentence count, reading time, language hint) from a given string — no LLM or network required.

## Facts

- Endpoint: POST https://agentshelf.syntexa.ch/v1/text-stats?utm_source=zero.xyz
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-01
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentshelf-text-statistics-de630c33
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_UVDVkRwptT4bVJPQ10AY9

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 agentshelf-text-statistics-de630c33 -d '<json body>'
```

Example prompt: Can you give me the word count, sentence count, character count, estimated reading time, and language hint for this text: 'Artificial intelligence is transforming industries at an unprecedented pace, reshaping how we work, communicate, and solve complex problems.'?

## When to prefer this

Choose this endpoint when you need fast, deterministic, offline-computable text metrics (word count, character count, sentence count, reading time, language hint) without incurring LLM inference costs or network latency. Ideal for lightweight content validation, readability checks, and preprocessing pipelines where accuracy of a statistical heuristic is sufficient and privacy matters (no text leaves the local compute context). Use the free sandbox endpoint POST /v1/sandbox/text-stats first to test; fall back to this paid endpoint for production use.

## Known failure modes

- Text exceeds 100,000 character limit — request rejected with a 4xx validation error
- Empty or whitespace-only text may yield zero counts and an ambiguous lang_hint
- Highly mixed-language text may produce an unreliable or generic lang_hint
- Payment failure or insufficient USDC balance returns a 402 Payment Required error

## How this service works

Call when an agent needs heuristic text stats: chars, words, sentences, reading_time_min, lang_hint. No LLM and no network. Exact $0.001 USDC. Prefer unpaid POST /v1/sandbox/text-stats first.

## Output

Returns a JSON object containing: chars (integer character count), words (integer word count), sentences (integer sentence count), reading_time_min (float estimated minutes to read at average reading speed), and lang_hint (string ISO language code or short label indicating the detected language).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "examples": [
    "Hello world. This is a short English paragraph for AgentShelf."
   ],
   "maxLength": 100000,
   "minLength": 0,
   "description": "Plain text to measure. No HTML parsing and no network."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentshelf-text-statistics-de630c33/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentshelf.syntexa.ch](https://www.zero.xyz/host/agentshelf.syntexa.ch/llms.txt)