# AxonGate Clean Context Broker – Web-to-Markdown Extraction

> AxonGate Clean Context Broker – Web-to-Markdown Extraction is a paid API for AI agents from api.axongate.one, paid per call via x402, $0.03/call, status unknown (last checked 2026-09-15).

Converts any public web URL into clean, readable Markdown text via a paid x402 micropayment endpoint

## Facts

- Endpoint: POST https://api.axongate.one/v1/x402/access
- Price: $0.03/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/api-axongate-one-a1ad4243
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Yx6f5VBa3NKgzgXwTWNpt

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 api-axongate-one-a1ad4243 -d '<json body>'
```

Example prompt: Fetch the article at https://example.com/blog/ai-trends and convert it into clean markdown using the fresh tier so I have up-to-date content.

## When to prefer this

Use this endpoint when an AI agent needs clean, LLM-ready Markdown from a live web page and is willing to pay $0.03 USDC per extraction. Prefer the 'fresh' tier for up-to-date content, 'cached' for cost savings on recently fetched pages, and 'deep' for JavaScript-rendered or complex pages. Ideal when HTML clutter, ads, and navigation boilerplate need to be removed before feeding content to a language model.

## Known failure modes

- Invalid or non-public URL returns 4xx error
- Payment insufficient for selected tier returns 402 with updated payment challenge
- Cached tier with force_refresh=true returns validation error
- Target URL is inaccessible or returns non-200 status
- Deep tier times out on very large or JavaScript-heavy pages

## How this service works

AxonGate context endpoint: paid clean Markdown extraction supporting the source trust layer.

## Output

Clean, readable Markdown text extracted from the target URL, stripped of HTML noise, ads, and boilerplate — suitable for direct use as LLM context or document input

## Example request

```json
{
 "tier": "fresh",
 "target_url": "https://example.com",
 "force_refresh": false
}
```

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "tier": {
   "enum": [
    "starter",
    "cached",
    "basic",
    "fresh",
    "deep"
   ],
   "type": "string",
   "default": "fresh",
   "description": "Payment tier. Standard x402 clients should also pass this as ?tier= or X-AxonGate-Tier so the challenge amount matches the request."
  },
  "target_url": {
   "type": "string",
   "format": "uri",
   "description": "Absolute public HTTP/HTTPS URL to convert into clean markdown."
  },
  "force_refresh": {
   "type": "boolean",
   "default": false,
   "description": "Bypass cache for cacheable tiers. Not supported for cached tier."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/api-axongate-one-a1ad4243/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.axongate.one](https://www.zero.xyz/host/api.axongate.one/llms.txt)