# AgentDiet Clean HTML — Context Window HTML Distiller

> AgentDiet Clean HTML — Context Window HTML Distiller 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).

Fetches a URL and strips HTML down to clean, token-efficient content, achieving up to 91%+ compression ratio for AI context windows

## Facts

- Endpoint: GET https://rag-diet.agentdiet.dev/v1/clean-html?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-clean-html-context-window-html-distiller-8804711e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_cgqrt6uUvXe9woVh7asfY

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-clean-html-context-window-html-distiller-8804711e
```

Example prompt: Can you clean and distill the HTML from https://example.com/article so I get only the essential text content with minimal tokens — I need to fit it into my context window without all the boilerplate noise?

## When to prefer this

Choose this endpoint when you need to reduce the token footprint of HTML web content before injecting it into an LLM context window — especially for RAG pipelines, multi-page research workflows, or cost-constrained agent loops where raw HTML would exceed limits or inflate costs. Prefer it over raw HTTP fetchers when token compression is the primary goal, and over generic web scrapers when you need a quantified ROI proof of compression. Best suited for single-URL, on-demand distillation via x402 micropayment at $0.001 USDC per call.

## Known failure modes

- Invalid or unreachable URL returns an error status
- URL that blocks bot/scraper access may return empty or error
- Very large pages may timeout or return partial content
- Malformed input schema (missing 'type' or 'method') returns validation error
- Pages behind authentication walls cannot be fetched
- Network errors reaching the target URL result in failed status

## 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 cleaned, distilled HTML/text content, a 'status' field ('ok'), and an 'roi_proof' object showing the compression_ratio_pct (e.g. 91.4%) achieved by the distillation — quantifying token savings.

## 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-clean-html-context-window-html-distiller-8804711e/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)