# PrepLayer.ai Text Chunker

> PrepLayer.ai Text Chunker is a paid API for AI agents from api.maximusmediahouse.com, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-29).

Splits long text into chunks for RAG retrieval pipelines using sentence-aware, paragraph-aware, or fixed-window strategies.

## Facts

- Endpoint: POST https://api.maximusmediahouse.com/v1/chunk?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-29
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/preplayer-ai-text-chunker-09e85bdb
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_gD65TlhWghWrZ20nHQKRm

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 preplayer-ai-text-chunker-09e85bdb -d '<json body>'
```

Example prompt: Take this 50,000-character article and split it into sentence-aware chunks of up to 1000 characters each so I can embed them for a RAG pipeline.

## When to prefer this

Choose this endpoint when you need deterministic, rule-based text chunking without LLM calls — especially when sentence or paragraph boundary preservation matters for RAG quality. It is faster and cheaper than model-based chunkers and supports large inputs up to 1M characters. Prefer it over manual splitting when you need overlap control or unicode-safe segmentation.

## Known failure modes

- Text exceeds 1,000,000 character limit — request rejected
- Overlap value equals or exceeds size value — invalid configuration error
- Invalid strategy enum value — validation error returned
- Empty text input — returns empty chunk array or error
- Network timeout on very large payloads close to the 1M char limit

## How this service works

Split long text into pieces for RAG retrieval. Strategies: 'sentence' packs whole sentences into a size budget and never splits mid-sentence; 'paragraph' prefers \n\n boundaries; 'fixed' is a hard char window with overlap. The highest-value endpoint for agents that build retrieval pipelines.

## Output

An array of text chunk strings, each respecting the requested size budget and strategy: sentence-aware chunks never break mid-sentence, paragraph chunks split at double-newline boundaries, and fixed chunks are hard character windows with optional overlap.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "size": {
   "type": "integer",
   "default": 1000,
   "maximum": 100000,
   "minimum": 1,
   "description": "Maximum chars per chunk."
  },
  "text": {
   "type": "string",
   "description": "Source text (1-1000000 chars)."
  },
  "overlap": {
   "type": "integer",
   "default": 200,
   "maximum": 99999,
   "minimum": 0,
   "description": "Overlap chars (fixed strategy only)."
  },
  "strategy": {
   "enum": [
    "fixed",
    "sentence",
    "paragraph"
   ],
   "type": "string",
   "default": "sentence",
   "description": "Splitting strategy."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/preplayer-ai-text-chunker-09e85bdb/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.maximusmediahouse.com](https://www.zero.xyz/host/api.maximusmediahouse.com/llms.txt)