# text-chunker-bulk

> text-chunker-bulk is a paid API for AI agents from intel.rallylive.ca, paid per call via x402, $0.1/call, status unknown (last checked 2026-09-14).

Fetches up to 20 URLs concurrently and returns RAG-ready text chunks for each, with per-item errors and a failure count, in input order.

## Facts

- Endpoint: GET https://intel.rallylive.ca/bulk/page/chunks
- Price: $0.1/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/text-chunker-bulk-4e46e1f3
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ND8sGfepIZRScl2OOk5bM

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 text-chunker-bulk-4e46e1f3
```

Example prompt: I have a list of 15 article URLs and I need all of them chunked into RAG-ready text segments in one go — can you run them all through the bulk text chunker and give me the results in the same order I gave you the URLs?

## When to prefer this

Choose this endpoint when you have a list of 2–20 URLs that all need to be chunked for RAG ingestion and you want a single concurrent call with ordered results and per-item error reporting, rather than making individual calls to the single /page/chunks endpoint sequentially. It is ideal for bulk knowledge-base construction, agent pipeline preprocessing, or any workflow where latency savings from concurrency matter.

## Known failure modes

- Invalid or unreachable URL returns a per-item error field with details while other items succeed
- Exceeding the 20-URL limit may result in rejection or partial processing
- Timeout on a specific URL populates that item's error field without failing the entire batch
- Malformed input (missing required 'input' object or 'method' field) returns a 400-level error
- Pages with no extractable text may return empty chunk arrays for that item

## How this service works

Bulk text chunker: up to 20 urls in one call, processed concurrently, results returned in input order with a per-item error field and a count of failures. Same answer per item as the single /page/chunks endpoint (Page to RAG chunks). Batch enrichment for agents that hold a list. $0.01 per batch.

## Output

An ordered array of results matching the input URL list, where each item contains RAG-ready text chunks (same output as the single /page/chunks endpoint) along with a per-item error field indicating success or failure. A top-level failure count summarizes how many items errored across the batch.

## 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",
     "properties": {}
    }
   },
   "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/text-chunker-bulk-4e46e1f3/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from intel.rallylive.ca](https://www.zero.xyz/host/intel.rallylive.ca/llms.txt)