{"uid":"cap_S2XMAU53wCmjZQR5sF_Yk","slug":"agentdiet-dev-agentdiet-dom-stripper-url-html-distillation-with-bm25-fa412b90","name":"AgentDiet DOM Stripper – URL/HTML Distillation 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://agentdiet.dev/v1/dom-stripper)","url":"https://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_02qcNXhN1CpJ4iqM4axr1","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"agentdiet.dev","brandSlug":"agentdiet-dev-mpp","brandBaseUrl":"https://agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into clean Markdown, structured JSON, a skeleton outline, or a BM25-ranked token-budget excerpt for LLM consumption","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it into clean markdown using budget mode, focused on 'payment intents', keeping it under 500 tokens so I don't blow my LLM budget.","exampleUseCases":[{"title":"Token-efficient research on live documentation","prompt":"Go to https://docs.openai.com/api-reference and distill the page into clean markdown, keeping the output under 800 tokens — I only care about content related to 'function calling'."},{"title":"Structured table extraction from a pricing page","prompt":"Fetch https://aws.amazon.com/ec2/pricing/ and distill it in structured mode so I get the pricing tables and metadata as JSON, not a wall of HTML."},{"title":"Skeleton outline of a long article before reading","prompt":"Grab https://en.wikipedia.org/wiki/Large_language_model and give me a skeleton outline of the page structure so I can decide which sections are worth reading in full."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd. Also includes cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns a fetch error with status non-ok","HTML payload too large may be truncated or rejected","BM25 budget mode with no query falls back to default ranking","max_tokens below minimum (20) triggers validation error","Paywalled or bot-blocked pages return empty or partial content","x402 payment required if no valid payment header is provided"],"whenToPreferThis":"Choose this endpoint when you need to feed web content to an LLM but want to minimize token usage and cost — especially when you have a strict token budget or a specific focus query. It is ideal over raw fetch-and-parse approaches because it provides built-in BM25 relevance ranking, multiple distillation modes (markdown, structured, skeleton, budget), and quantified ROI metrics showing exactly how many tokens and dollars were saved. Prefer it over generic scrapers when working with documentation pages, pricing tables, or long articles where only a subset of content is relevant.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:36:33.703Z","isFirstParty":false,"canonicalSlug":"agentdiet-dev-agentdiet-dom-stripper-url-html-distillation-with-bm25-fa412b90"}