# AgentToll LLM Pack Batch

> AgentToll LLM Pack Batch is a paid API for AI agents from agent-toll.agentfetcher.workers.dev, paid per call via x402, $0.015/call, status unknown (last checked 2026-09-14).

Fetches up to 5 public URLs in a single x402 payment and returns each as token-budgeted LLM-ready markdown for multi-source research and RAG ingestion

## Facts

- Endpoint: GET https://agent-toll.agentfetcher.workers.dev/v1/llm-pack-batch
- Price: $0.015/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agenttoll-llm-pack-batch-81243d05
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Inl4WFcYs-UEHCcL9hr6C

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 agenttoll-llm-pack-batch-81243d05
```

Example prompt: Fetch these 5 pages and convert them all to clean LLM-ready markdown in one go — limit each to 6000 tokens: https://en.wikipedia.org/wiki/Retrieval-augmented_generation, https://arxiv.org/abs/2005.11401, https://www.pinecone.io/learn/rag, https://docs.llamaindex.ai/en/stable/getting_started/concepts/, https://huggingface.co/blog/rag

## When to prefer this

Choose this endpoint when you need to fetch and convert multiple (2–5) public web pages to LLM-ready markdown in a single round-trip and payment. It is more efficient than calling the single-URL llm-pack endpoint repeatedly and is specifically designed for multi-hop agents, deep research workflows, and multi-source RAG ingestion where per-URL error isolation matters.

## Known failure modes

- One or more URLs are inaccessible (403, 404, timeout) — that URL's entry contains an error field while others succeed
- More than 5 URLs submitted — request rejected
- Payment not completed or x402 challenge not resolved — 402 response returned
- URL points to non-public or paywalled content — returned content may be partial or empty
- maxTokens outside 500–32000 range — validation error

## How this service works

x402 probe surface for llm-pack-batch. Real usage: POST {urls[]}. Unpaid → 402. Optional bid header supported.

## Output

A batch response containing one entry per input URL, each with LLM-ready markdown, token-budgeted to maxTokens (default 4000). Per-URL errors are isolated so a failure on one URL does not cancel the others. Useful for feeding multiple sources directly into LLM context windows or RAG pipelines.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "urls": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "description": "1–5 public URLs to pack into LLM-ready markdown in one payment (research / multi-source RAG)"
  },
  "noCache": {
   "type": "boolean",
   "description": "Skip cache for all URLs"
  },
  "maxTokens": {
   "type": "number",
   "description": "Per-URL token budget (500–32000, default 4000)"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agenttoll-llm-pack-batch-81243d05/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-toll.agentfetcher.workers.dev](https://www.zero.xyz/host/agent-toll.agentfetcher.workers.dev/llms.txt)