{"uid":"cap_HdHzKFgHhJtvW-hCBIGMc","slug":"hn-pulse-agentdiet-dev-web-url-distiller-with-bm25-budget-control-6f429f13","name":"Web URL 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://hn-pulse.agentdiet.dev/v1/web-scrape)","url":"https://hn-pulse.agentdiet.dev/v1/web-scrape?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_eC919jjuo-fVnQAOuGG3c","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 markdown, structured JSON, skeleton outline, or BM25-focused token-budgeted excerpts","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments into compact markdown so I can read it without burning too many tokens — use budget mode with a focus query on 'payment intents' and cap it at 500 tokens?","exampleUseCases":[{"title":"Token-efficient documentation reading","prompt":"Distill https://docs.openai.com/api-reference into structured markdown for me — I want the cleanest possible version without all the nav clutter, using markdown mode."},{"title":"BM25 focused research extraction","prompt":"Scrape https://en.wikipedia.org/wiki/Large_language_model and give me only the parts relevant to 'training data', budget mode with a max of 300 tokens so I don't blow my context window."},{"title":"Competitive intel page summarization","prompt":"Pull the content from https://www.anthropic.com/product and distill it into a skeleton outline so I can quickly see the structure of what they're offering without reading the whole page."}],"resultDescription":"Returns a 'data' object containing the distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object with raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd, along with cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","Paywalled or bot-blocked pages may return empty or partial content","max_tokens too low (below 20) returns a validation error","BM25 query with no matching content returns minimal output","Raw HTML too large may time out or be truncated","x402 payment failure prevents endpoint access"],"whenToPreferThis":"Choose this endpoint when an agent needs to read web content but wants to minimize token consumption — especially useful when processing documentation pages, long articles, or data-heavy sites. Prefer over raw fetch+parse when token budget control via BM25 or a strict max_tokens ceiling is needed. The built-in compression ROI reporting makes it easy to audit cost savings per call. Best suited for single-URL distillation with structured or markdown output requirements.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:26:20.495Z","isFirstParty":false,"canonicalSlug":"hn-pulse-agentdiet-dev-web-url-distiller-with-bm25-budget-control-6f429f13"}