# workbot1.oddsys.org Document Chunker

> workbot1.oddsys.org Document Chunker is a paid API for AI agents from workbot1.oddsys.org, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-12).

Splits a document into token-bounded chunks at natural boundaries (paragraphs/sentences) with optional overlap, producing ready-to-embed pieces for RAG pipelines.

## Facts

- Endpoint: POST https://workbot1.oddsys.org/chunk?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/workbot1-oddsys-org-document-chunker-312b83cb
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_f8wa_Sk1f8ExKPfY_kwB-

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 workbot1-oddsys-org-document-chunker-312b83cb -d '<json body>'
```

Example prompt: Split this article into chunks of at most 512 tokens, breaking at paragraph boundaries, with a 50-token overlap between chunks so it's ready to embed for my RAG pipeline.

## When to prefer this

Use this endpoint when you need to prepare long documents for RAG or semantic search and want token-aware, boundary-respecting chunking done as a lightweight, off-context API call — avoiding burning LLM tokens on splitting logic. Prefer it over rolling your own chunking when you need reliable paragraph- or sentence-level splits with configurable overlap and token bounds, especially in automated pipelines ingesting many documents.

## Known failure modes

- Document text is empty or missing — returns error indicating no content to chunk
- Token limit set too low to fit even a single sentence — may return error or single-token fragments
- Unsupported boundary type specified — returns validation error
- Request body malformed or missing required fields — returns 400-level error
- Payment not included or insufficient — returns 402 Payment Required

## How this service works

Split a document into token-bounded chunks at natural boundaries (paragraphs/sentences), with optional overlap. Ready-to-embed pieces for RAG, no tokens spent on the splitting logic.

## Output

An ordered list of text chunks, each bounded by the specified token limit and split at natural boundaries (paragraphs or sentences), with optional overlapping tokens between adjacent chunks — ready to pass directly to an embedding model or vector store.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "The document text to split into chunks."
  },
  "maxTokens": {
   "type": "number",
   "description": "Target max tokens per chunk (32–8000, default 512)."
  },
  "overlapTokens": {
   "type": "number",
   "description": "Trailing tokens overlapped into each chunk (default 0)."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/workbot1-oddsys-org-document-chunker-312b83cb/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from workbot1.oddsys.org](https://www.zero.xyz/host/workbot1.oddsys.org/llms.txt)