{"uid":"cap_vXnUafUbuoUdYbBcgeJXp","slug":"hn-pulse-agentdiet-dev-dom-stripper-web-url-distiller-5560840c","name":"DOM Stripper — Web URL Distiller","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://hn-pulse.agentdiet.dev/v1/dom-stripper)","url":"https://hn-pulse.agentdiet.dev/v1/dom-stripper?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"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"}}},"responseSchema":{"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"}}}}},"example":null,"exampleRequest":null,"tags":[],"displayCostAmount":"0.001","displayCostAsset":"USD","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.001/call","primary":{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.001","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_hgfxdzRhR_2S6tCdh7X8J","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"hn-pulse.agentdiet.dev","brandSlug":"hn-pulse-agentdiet-dev-mpp","brandBaseUrl":"https://hn-pulse.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or raw HTML and distills it into compact, agent-ready tokens using markdown, structured, skeleton, or BM25 budget-controlled extraction modes","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into compact markdown and keep it under 800 tokens, focusing on 'payment intent' so I can feed it to my agent without blowing my context window.","exampleUseCases":[{"title":"Token-budget research on live docs","prompt":"Fetch https://docs.openai.com/api-reference and distill it in budget mode with a max of 500 tokens, using 'function calling' as the focus query — I need just the relevant bits for my agent."},{"title":"Structured data extraction from a product page","prompt":"Strip https://www.apple.com/iphone-16/ into structured mode so I get JSON tables of specs and metadata — no boilerplate HTML, just the clean data."},{"title":"Outline skeleton of a long article","prompt":"Give me a skeleton outline of https://en.wikipedia.org/wiki/Large_language_model so I can see the section structure before deciding which parts to read in full."}],"resultDescription":"Returns a 'data' object containing the distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), along with an roi_proof block showing raw token count, distilled token count, tokens saved, compression ratio percentage, LLM cost saved in USD, and ROI multiplier. Also includes optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns a non-200 status — endpoint may return an error status","HTML payload is malformed or empty — distillation may produce empty or minimal output","max_tokens set too low (below 20) — rejected by schema validation","mode=budget used without a query parameter — BM25 ranking has no focus term","Payment not provided or insufficient for x402 — returns HTTP 402 Payment Required","Rate limiting or timeout on fetching the target URL — slow or failed response"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web content within a strict token budget and you want both retrieval and compression in a single paid call. It is especially useful when you need BM25-focused extraction (surfacing only the most query-relevant content), when you need structured JSON tables from a page, or when you need a skeleton outline for navigation. Prefer it over generic scrapers when token cost reduction and ROI proof matter — the response explicitly reports how many tokens and dollars were saved.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:47.656Z","isFirstParty":false,"canonicalSlug":"hn-pulse-agentdiet-dev-dom-stripper-web-url-distiller-5560840c"}