# AgentDiet Context Diet – HTML Semantic Distillation

> AgentDiet Context Diet – HTML Semantic Distillation is a paid API for AI agents from agentdiet.dev, paid per call via x402 or MPP, $0.001/call, status unknown (last checked 2026-10-20).

Strips 85–97% of HTML token bloat from a given URL, returning only the semantically meaningful content for LLM consumption

## Facts

- Endpoint: GET https://agentdiet.dev/v1/context-diet?utm_source=zero.xyz
- Price: $0.001/call
- Payment: x402, MPP
- Status: unknown
- Last checked: 2026-10-20
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentdiet-context-diet-html-semantic-distillation-cffe406e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_9i5L72CgZXhHxoA_peZhy

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-context-diet-html-semantic-distillation-cffe406e
```

Example prompt: Fetch https://example.com/article and strip out all the HTML token bloat so I get just the clean, meaningful text — I need to fit it into my LLM context window.

## When to prefer this

Choose this endpoint when you need to feed a webpage into an LLM but the raw HTML is too token-heavy for your context window. It is purpose-built for token optimization and semantic distillation, making it ideal for RAG pipelines, agent web-browsing steps, or any workflow where HTML bloat would waste tokens or exceed context limits. Prefer this over generic web scrapers when token efficiency is the primary concern.

## Known failure modes

- URL is unreachable or returns a non-200 status — endpoint may return an error or empty content
- URL points to a JavaScript-heavy SPA that requires client-side rendering — distilled output may be sparse
- Paywalled or auth-gated pages return only login-wall content
- Very large pages may time out or return partial content
- Malformed URL input causes a 400-level error
- The page is already minimal HTML with little to strip, resulting in near-identical output

## How this service works

Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://agentdiet.dev/v1/context-diet)

## Output

A token-compressed, semantically distilled version of the target webpage's content — stripped of 85–97% of HTML markup, navigation, scripts, and boilerplate — returning only the meaningful prose, headings, and data for direct LLM ingestion.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "url"
 ],
 "properties": {
  "url": {
   "type": "string",
   "minLength": 1,
   "description": "Target webpage URL to fetch and distill (or builtin://stripe-docs)"
  },
  "html": {
   "type": "string",
   "description": "Optional raw HTML string to distill directly without fetching"
  },
  "mode": {
   "enum": [
    "markdown",
    "structured",
    "skeleton",
    "budget"
   ],
   "type": "string",
   "default": "markdown",
   "description": "Distillation mode"
  },
  "query": {
   "type": "string",
   "description": "BM25 focus query when mode=budget"
  },
  "max_tokens": {
   "type": "integer",
   "minimum": 20,
   "description": "Strict token budget ceiling when mode=budget"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "status",
  "roi_proof",
  "data"
 ],
 "properties": {
  "data": {
   "type": "object",
   "description": "Distilled Markdown, structured JSON tables/metadata, skeleton outline, or BM25 budget excerpt."
  },
  "cache": {
   "type": "object",
   "properties": {
    "status": {
     "enum": [
      "HIT",
      "MISS"
     ],
     "type": "string"
    },
    "cache_key": {
     "type": "string"
    },
    "latency_ms": {
     "type": "number"
    }
   }
  },
  "status": {
   "type": "string",
   "description": "Execution status ('ok')"
  },
  "billing": {
   "type": "object",
   "properties": {
    "agent_id": {
     "type": "string"
    },
    "payment_method": {
     "type": "string"
    },
    "fee_charged_usd": {
     "type": "number"
    }
   }
  },
  "roi_proof": {
   "type": "object",
   "properties": {
    "raw_tokens": {
     "type": "integer"
    },
    "tokens_saved": {
     "type": "integer"
    },
    "roi_multiplier": {
     "type": "number"
    },
    "distilled_tokens": {
     "type": "integer"
    },
    "llm_cost_saved_usd": {
     "type": "number"
    },
    "compression_ratio_pct": {
     "type": "number"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentdiet-context-diet-html-semantic-distillation-cffe406e/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentdiet.dev](https://www.zero.xyz/host/agentdiet.dev/llms.txt)