# AgentDiet DOM Stripper — Context Window Token Compressor

> AgentDiet DOM Stripper — Context Window Token Compressor is a paid API for AI agents from rag-diet.agentdiet.dev, paid per call via x402, $0.001/call, status unknown (last checked 2026-10-22).

Strips and compresses HTML/DOM content from a URL to reduce token usage by up to 91% for AI context windows

## Facts

- Endpoint: GET https://rag-diet.agentdiet.dev/v1/dom-stripper?utm_source=zero.xyz
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-22
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentdiet-dom-stripper-context-window-token-compressor-b7cae17d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_bTrAbfV0JBGsmSzXCfrrT

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 agentdiet-dom-stripper-context-window-token-compressor-b7cae17d
```

Example prompt: Strip and compress the HTML from https://example.com/article using GET mode so I get just the clean, token-efficient text — I need to fit it into my AI context window without burning tokens on nav menus and boilerplate.

## When to prefer this

Choose this endpoint when you need to feed live web content into an LLM or RAG pipeline and want to aggressively reduce token count before passing content downstream. It is especially useful when context windows are constrained, when scraping many pages on a token budget, or when building agent workflows that must access web content cheaply. Prefer it over raw HTML fetching or generic text extractors when you need a provable compression ratio and structured JSON output.

## Known failure modes

- Invalid or unreachable URL returns error status
- Unsupported content type (non-HTML) may yield poor compression or error
- Rate limit or payment failure (x402) if USDC payment not settled
- Timeout on slow-loading target pages
- Empty or near-empty page yields low compression ratio

## How this service works

Deterministic B2A/A2A/MCP/x402/MPP/L402 execution and intelligence node at https://rag-diet.agentdiet.dev settling in USDC on Base.

## Output

Returns a JSON object with a 'data' field containing the distilled/compressed content, a 'status' field ('ok' on success), and an 'roi_proof' object showing the compression_ratio_pct achieved (e.g. 91.4% token reduction).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET",
      "POST"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "properties": {
      "url": {
       "type": "string"
      },
      "mode": {
       "type": "string"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "data": {},
  "status": "ok",
  "roi_proof": {
   "compression_ratio_pct": 91.4
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentdiet-dom-stripper-context-window-token-compressor-b7cae17d/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from rag-diet.agentdiet.dev](https://www.zero.xyz/host/rag-diet.agentdiet.dev/llms.txt)