{"uid":"cap_mEZZknSNtOZeHISQK9P7M","slug":"domain-osint-agentdiet-dev-web-distillation-with-bm25-budget-control-36b1658c","name":"Web 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://domain-osint.agentdiet.dev/v1/dom-stripper)","url":"https://domain-osint.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_boBTZ2WsT0C6iaRNH0W98","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"domain-osint.agentdiet.dev","brandSlug":"domain-osint-agentdiet-dev-mpp","brandBaseUrl":"https://domain-osint.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into Markdown, structured JSON, an outline skeleton, or a BM25-focused token-budgeted excerpt","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into clean markdown using budget mode, focused on the query 'payment intents', and keep it under 500 tokens.","exampleUseCases":[{"title":"Token-efficient doc reading for agents","prompt":"Fetch https://docs.openai.com/api-reference and distill it in budget mode with the query 'function calling' and a max of 300 tokens — I need to stay within my context window."},{"title":"Clean markdown extraction from noisy page","prompt":"Grab the HTML from this URL https://techcrunch.com/2024/05/01/some-article and strip out all the nav, ads, and boilerplate — just give me the article body as clean markdown."},{"title":"Structured data extraction from a webpage","prompt":"Distill https://en.wikipedia.org/wiki/List_of_countries_by_GDP in structured mode so I get the tables as JSON rather than raw HTML."}],"resultDescription":"Returns a 'data' object containing the distilled content in the requested format (Markdown string, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt), plus ROI proof metrics (raw tokens, distilled tokens, compression ratio, tokens saved, estimated LLM cost saved in USD), optional cache hit/miss status with latency, and billing details.","failureModes":["Invalid or unreachable URL returns an error status","HTML fetch timeout for slow or blocked domains","max_tokens set below minimum of 20 returns validation error","mode=budget without a query may yield unguided truncation","Payment/402 failure if USDC balance is insufficient","Raw HTML too large may exceed processing limits"],"whenToPreferThis":"Use this endpoint when an AI agent needs to read web content but must stay within a token budget or minimize LLM costs. It is especially valuable when a raw page is too noisy or large to pass directly to an LLM. The BM25 budget mode is uniquely suited for focused retrieval — providing only the passages most relevant to a specific query. Prefer this over generic scrapers when you need ROI metrics (tokens saved, compression ratio) or structured JSON output alongside distilled content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:34:40.206Z","isFirstParty":false,"canonicalSlug":"domain-osint-agentdiet-dev-web-distillation-with-bm25-budget-control-04fd791d"}