# AgentTools Text Chunker

> AgentTools Text Chunker is a paid API for AI agents from agentstoolshub.com, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-12).

Splits raw text into token-budget-aware, sentence-boundary-respecting chunks with configurable overlap for RAG pipeline preparation.

## Facts

- Endpoint: GET https://agentstoolshub.com/api/v1/dev/text-chunker?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/agenttools-text-chunker-003b29ba
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_4U99mLJTVKQTg30Rb1pmV

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 agenttools-text-chunker-003b29ba
```

Example prompt: Can you chunk this article into segments of about 256 tokens each, with 32 tokens of overlap between chunks, so I can embed them for a RAG pipeline?

## When to prefer this

Choose this endpoint when you need deterministic, sentence-aware text chunking with precise token budgets and configurable overlap — especially as a preprocessing step before embedding or vector store ingestion. Prefer this over naive character-splitting when context continuity across chunks matters, or when you need to respect token limits of embedding models without cutting mid-sentence.

## Known failure modes

- Missing required 'text' query parameter returns 400 error
- Extremely short text with a large token target may return a single unsplit chunk
- Non-numeric values for targetTokens or overlapTokens cause validation errors
- Very large input text may hit request size limits
- Overlap value equal to or greater than targetTokens may cause infinite or degenerate chunking

## How this service works

Split text into retrieval-friendly chunks with a token budget and sentence-aware boundaries. Overlap between consecutive chunks preserves context across splits — the standard preparation step before embedding. Use this when an agent needs to rAG-ready chunks with token budgets and overlap.

## Output

Returns an array of text chunks derived from the input, each respecting sentence boundaries and staying within the specified token budget. Consecutive chunks share an overlapping token window to preserve context across splits. Likely includes chunk index, token count per chunk, and the chunk text itself.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "text"
     ],
     "properties": {
      "text": {
       "type": "string",
       "description": "Text"
      },
      "targetTokens": {
       "type": "number",
       "description": "Target tokens per chunk"
      },
      "overlapTokens": {
       "type": "number",
       "description": "Overlap tokens"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agenttools-text-chunker-003b29ba/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentstoolshub.com](https://www.zero.xyz/host/agentstoolshub.com/llms.txt)