{"uid":"cap_8FH_eAfTlklHyAqBpuNQa","slug":"defi-yield-agentdiet-dev-dom-stripper-url-html-distiller-with-bm25-384a3e6b","name":"DOM Stripper — URL & HTML Distiller with BM25 Budget Control","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://defi-yield.agentdiet.dev/v1/dom-stripper)","url":"https://defi-yield.agentdiet.dev/v1/dom-stripper?utm_source=zero.xyz","method":"POST","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_CPzJ1UBIUgxw6KgieHVoZ","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"defi-yield.agentdiet.dev","brandSlug":"defi-yield-agentdiet-dev-mpp","brandBaseUrl":"https://defi-yield.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into compact Markdown, structured JSON, a skeleton outline, or a BM25-ranked token-budgeted excerpt","exampleAgentPrompt":"Fetch https://docs.stripe.com/payments/checkout and distill it into clean Markdown using budget mode, focused on 'payment intent setup', keeping it under 500 tokens.","exampleUseCases":[{"title":"Distill documentation page for LLM context","prompt":"Grab https://platform.openai.com/docs/guides/function-calling and distill it into clean Markdown so I can feed it to my agent without blowing my context window."},{"title":"Extract structured data from competitor pricing page","prompt":"Fetch https://www.notion.so/pricing and pull out the pricing tiers and features as structured JSON tables — I want to compare plans."},{"title":"BM25 budget excerpt for research query","prompt":"Distill https://arxiv.org/abs/2310.06825 using budget mode, focused on the query 'retrieval augmented generation evaluation', and keep it under 300 tokens so it fits in my prompt."}],"resultDescription":"Returns a JSON object with 'data' containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio %, ROI multiplier, and estimated LLM cost saved in USD, a cache status (HIT/MISS), and billing details.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error status","Raw HTML is malformed or empty — distillation may return minimal content","Token budget too low (below 20) — rejected by schema validation","BM25 query not provided when mode=budget — may default to full distillation","Page is JavaScript-rendered SPA with no static HTML — content may be sparse","Rate limit or payment failure — 402 response if USDC payment not attached"],"whenToPreferThis":"Choose this endpoint when you need to feed web content to an LLM and must control token usage — especially when mode=budget with a BM25 query lets you extract only the most relevant passages. Prefer over generic scrapers when you need built-in compression metrics (ROI proof, tokens saved) and multiple output formats (Markdown, structured JSON, skeleton, budget excerpt). Ideal for agentic pipelines that need to stay within strict context window limits.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:31:01.103Z","isFirstParty":false,"canonicalSlug":"defi-yield-agentdiet-dev-dom-stripper-url-html-distiller-with-bm25-384a3e6b"}