{"uid":"cap_RY15glrhwJPKUhOwv5jXn","slug":"domain-osint-agentdiet-dev-webpage-distiller-with-bm25-budget-control-c147a6bc","name":"Webpage 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://domain-osint.agentdiet.dev/v1/webpage-distiller)","url":"https://domain-osint.agentdiet.dev/v1/webpage-distiller?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_ravGJofjntGReDBhsw-OX","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 clean Markdown, structured JSON, a skeleton outline, or a BM25-ranked token-budgeted excerpt","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/payments and distill it into clean markdown, staying under 800 tokens, focused on the query 'payment intents API'?","exampleUseCases":[{"title":"Compress docs page for LLM context","prompt":"Grab the page at https://docs.openai.com/api-reference/chat and distill it into markdown keeping it under 500 tokens — I need to fit it into a prompt without wasting context."},{"title":"Extract relevant section with BM25 focus","prompt":"Distill https://www.sec.gov/cgi-bin/browse-edgar?action=getcurrent in budget mode, focused on the query 'annual 10-K filings', with a max of 300 tokens — I only want the parts relevant to annual reports."},{"title":"Turn raw HTML into structured data","prompt":"I have some raw HTML from a product listing page — can you distill it in structured mode to pull out the tables and metadata as JSON?"}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown string, 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 optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 status — service may return an error status","Token budget too low (below 20) — rejected by schema validation","Invalid mode enum value — request rejected","Raw HTML is malformed or empty — distillation may produce poor output","Rate limiting or payment failure via x402 — billing error returned","Target page blocks automated fetching (anti-bot) — content may be incomplete"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read a webpage but must stay within a strict token budget, or when raw HTML needs to be cleaned and structured before passing to an LLM. It is especially valuable for BM25-focused retrieval where only the most query-relevant tokens from a large page are needed, reducing LLM cost. Prefer it over generic scrapers when ROI/compression metrics matter, or when the output must be in a specific format (Markdown, structured JSON, skeleton, or budget excerpt).","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:32:59.443Z","isFirstParty":false,"canonicalSlug":"domain-osint-agentdiet-dev-webpage-distiller-with-bm25-budget-control-c147a6bc"}