# agentread snapshot/get

> agentread snapshot/get is a paid API for AI agents from agentread.midi-thumb.workers.dev, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-31).

Fetches the readable text of a URL that an agent's own HTTP request failed on (403, 429, empty body, JS shell), returning the page content or a structured failure verdict.

## Facts

- Endpoint: POST https://agentread.midi-thumb.workers.dev/snapshot/get?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-31
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentread-snapshot-get-509d1891
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_JdhWOgRQVbb1UZMKfBTLl

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 agentread-snapshot-get-509d1891 -d '<json body>'
```

Example prompt: I just tried to fetch https://example.com/article but got a 403 — can you use agentread to grab the page text for me anyway?

## When to prefer this

Use this endpoint as a fallback when your own HTTP fetch returns 403, 429, an empty body, or a JavaScript-only shell with no meaningful content. It is specifically designed for agents that have already tried and failed to fetch a URL directly, making it ideal for resilient web-reading pipelines. Prefer it over a general scraping service when you need a quick, pay-per-use single-URL fallback with no setup.

## Known failure modes

- URL is behind a hard login wall — returns a verdict explaining authentication is required
- Page is a genuine captcha gate with no bypassable content — returns failure verdict
- Target server is completely unreachable or DNS fails — returns error verdict
- Content is binary or non-text (PDF, image) — may return empty or partial text
- Rate limits on the agentread service itself if called excessively

## How this service works

Read a URL your own fetch failed on and get the page text back, or a verdict explaining why it cannot be read. Built for agents that just got a 403, 429, empty body or JS shell.

## Output

Returns a JSON object containing the extracted plain text of the requested page under the 'text' field and a 'snapshot_id' string identifying the cached snapshot. If the page cannot be read, returns a verdict explaining why (e.g. login required, truly empty, paywall).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "const": "http"
    },
    "method": {
     "const": "POST"
    }
   },
   "additionalProperties": true
  },
  "output": {
   "type": "object",
   "additionalProperties": true
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "text": "…",
  "snapshot_id": "a1b2c3d4e5f6a7b8"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentread-snapshot-get-509d1891/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentread.midi-thumb.workers.dev](https://www.zero.xyz/host/agentread.midi-thumb.workers.dev/llms.txt)