# AI Crawler Access Triage

> AI Crawler Access Triage is a paid API for AI agents from tizona-outpost.venusberg.workers.dev, paid per call via x402, $0.001/call, status unknown (last checked 2026-09-14).

Bulk-checks how websites treat AI crawlers (GPTBot, ClaudeBot) and normal browsers, returning per-URL access verdicts (served, refused, or tollgated) from a standing census.

## Facts

- Endpoint: POST https://tizona-outpost.venusberg.workers.dev/v1/oracle/triage
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/ai-crawler-access-triage-ce9c1933
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ec-4l8FFfJxS9JkGxoFWy

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 ai-crawler-access-triage-ce9c1933 -d '<json body>'
```

Example prompt: Check these 50 URLs and tell me which ones block GPTBot or ClaudeBot versus which ones serve them normally — I need to know if any are tollgating or outright refusing AI crawlers before I try to fetch them.

## When to prefer this

Use this endpoint when you need to bulk-assess AI crawler accessibility across many URLs before attempting to fetch them, or when you want to detect robots.txt, paywall, or bot-block changes over time. It is more efficient than checking each URL individually and covers GPTBot, ClaudeBot, and normal browser access in a single call.

## Known failure modes

- Exceeding 200 URLs per request returns an error
- Malformed URLs in the array may produce null or error verdicts per entry
- URLs very recently added to the census may have stale or incomplete data
- Network timeouts to the census backend may delay or drop responses

## How this service works

Check how websites treat AI crawlers, in bulk. POST {"urls":[...]} (up to 200) to get per-URL access verdicts for GPTBot, ClaudeBot, and a normal browser — served, refused, or tollgated — from a standing census, with a summary. Unknown URLs are added to the census and returned free; you are charged only for URLs already known. For agents deciding what they can fetch, and for spotting robots.txt, paywall, or bot-block changes over time.

## Output

A per-URL breakdown of access verdicts for GPTBot, ClaudeBot, and a normal browser — each labeled as 'served', 'refused', or 'tollgated' — plus an overall summary. Unknown URLs are added to the census and returned free; already-known URLs incur a charge.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "urls": {
   "type": "array",
   "items": {
    "type": "string"
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/ai-crawler-access-triage-ce9c1933/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from tizona-outpost.venusberg.workers.dev](https://www.zero.xyz/host/tizona-outpost.venusberg.workers.dev/llms.txt)