{"uid":"cap_W9XlKtGGMzckMJLwc-VZV","slug":"hn-pulse-agentdiet-dev-web-url-distillation-bm25-budget-extraction-a0db20da","name":"Web URL Distillation & BM25 Budget Extraction","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/paywall-clean-extract)","url":"https://hn-pulse.agentdiet.dev/v1/paywall-clean-extract?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_ATbAboS-HKViovapo90DB","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":"Distill the content at https://stripe.com/docs/payments into clean Markdown and keep it under 1000 tokens, focusing on payment integration steps.","exampleUseCases":[{"title":"Token-budgeted research article extraction","prompt":"Fetch https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) and give me a BM25-focused excerpt about attention mechanisms, keeping it under 500 tokens."},{"title":"Structured table extraction from a webpage","prompt":"Pull the content from https://coinmarketcap.com/all/views/all/ and return it as structured JSON tables so I can see the token prices and market caps cleanly."},{"title":"Skeleton outline of a long documentation page","prompt":"Get the skeleton outline of https://docs.anthropic.com/en/docs/overview so I can see the high-level structure without reading the whole page."}],"resultDescription":"Returns a 'data' object containing distilled content in the requested mode (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25 budget excerpt), plus an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, LLM cost saved in USD, and ROI multiplier. Also includes optional cache status and billing info.","failureModes":["Invalid or unreachable URL returns an error status","Paywalled content may not be fully extractable","Token budget too small (below 20) returns a validation error","Raw HTML too large may exceed processing limits","Unsupported mode enum value returns a schema error","Network timeout fetching target URL returns a fetch error"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read web content but must conserve LLM context tokens — especially for long documentation pages, articles, or data tables. Ideal when you need BM25-focused topic extraction within a strict token ceiling, or when you want structured JSON tables or skeleton outlines instead of raw HTML. Prefer over generic scraping tools when token efficiency and ROI metrics matter.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:25.311Z","isFirstParty":false,"canonicalSlug":"hn-pulse-agentdiet-dev-web-url-distillation-bm25-budget-extraction-a0db20da"}