# AgentCarWash LLM Pack Batch

> AgentCarWash LLM Pack Batch is a paid API for AI agents from agent-carwash.agentfetcher.workers.dev, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-14).

Fetches up to 5 public URLs in a single payment and returns each as LLM-ready markdown, with per-URL error isolation.

## Facts

- Endpoint: POST https://agent-carwash.agentfetcher.workers.dev/v1/llm-pack-batch
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentcarwash-llm-pack-batch-c131e4eb
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_99lyvIGB_uLT1kOLS44JN

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 agentcarwash-llm-pack-batch-c131e4eb -d '<json body>'
```

Example prompt: Fetch these 5 pages and give me clean LLM-ready markdown for each — https://example.com/a, https://example.com/b, https://example.com/c, https://example.com/d, https://example.com/e — with a 6000 token budget per URL so I can use them all for my research pipeline.

## When to prefer this

Choose this endpoint when you need to fetch and convert multiple (2–5) public web pages into LLM-ready markdown in a single payment transaction, especially for multi-hop research agents, RAG ingest pipelines, or any workflow where batching reduces overhead compared to calling a single-URL endpoint repeatedly.

## Known failure modes

- Individual URLs that are inaccessible, paywalled, or return non-200 responses yield per-URL error objects while others succeed
- Submitting more than 5 URLs may be rejected or truncated
- maxTokens outside the 500–32000 range may cause validation errors
- Payment failure via x402 protocol returns 402 with payment requirements
- Network timeouts on slow-loading pages may cause per-URL failures
- Private or localhost URLs will not be fetched

## How this service works

Multi-URL research pack: convert up to 5 public pages into LLM-ready markdown in one x402 payment. For deep research, multi-hop agents, and RAG ingest. $0.02 USDC Base. Body: {urls[], maxTokens?}. Per-URL errors isolated.

## Output

Returns a batch response containing one entry per input URL: each entry includes LLM-ready markdown of the page content, truncated to the specified token budget. Per-URL errors are isolated so a single failed URL does not block the rest of the results.

## 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/agentcarwash-llm-pack-batch-c131e4eb/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-carwash.agentfetcher.workers.dev](https://www.zero.xyz/host/agent-carwash.agentfetcher.workers.dev/llms.txt)