{"uid":"cap_aTaioS4Um-AbxVc7NSm1I","slug":"github-audit-agentdiet-dev-web-page-distiller-bm25-token-budget-9d6383e7","name":"Web Page Distiller – BM25 Token Budget Compression","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://github-audit.agentdiet.dev/v1/webpage-distiller)","url":"https://github-audit.agentdiet.dev/v1/webpage-distiller?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_jonl78ezt92YTC0QgjHt4","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"github-audit.agentdiet.dev","brandSlug":"github-audit-agentdiet-dev-mpp","brandBaseUrl":"https://github-audit.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or raw HTML and distills it into compact, agent-ready tokens using markdown, structured, skeleton, or BM25 budget modes","exampleAgentPrompt":"Can you distill https://stripe.com/docs/api into compact markdown and keep it under 800 tokens, focusing on the 'authentication' section?","exampleUseCases":[{"title":"Documentation page for LLM context","prompt":"Grab the Stripe docs at https://stripe.com/docs/payments and distill them into clean markdown — keep it under 600 tokens so I can fit it in my prompt."},{"title":"Focused research excerpt from news article","prompt":"Distill https://techcrunch.com/2024/05/01/openai-gpt5-launch into a BM25 budget excerpt focused on 'pricing and availability', max 300 tokens."},{"title":"Structured product data from e-commerce page","prompt":"Fetch https://www.apple.com/shop/buy-iphone and distill it in structured mode so I get a clean JSON table of products, prices, and variants."}],"resultDescription":"Returns a 'data' object containing the distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt), plus an 'roi_proof' object showing raw vs distilled token counts, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and a billing record with fee charged.","failureModes":["Invalid or unreachable URL returns an error status","HTML too large or malformed may produce incomplete distillation","BM25 budget mode without a query falls back to default behavior","max_tokens below minimum (20) returns validation error","Paywalled or bot-blocked pages may return empty or partial content","Payment required (HTTP 402) if no valid x402 payment is attached"],"whenToPreferThis":"Choose this endpoint when you need to compress web content into a minimal token footprint before passing it to an LLM, especially when operating under strict context-window or cost constraints. It is preferable to generic scrapers when you need BM25-ranked relevance filtering, multiple distillation modes (markdown/structured/skeleton/budget), and built-in ROI metrics showing tokens and cost saved. Ideal for agent pipelines where fetching and summarizing external documentation, product pages, or news articles needs to happen cheaply and at scale.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:50:12.912Z","isFirstParty":false,"canonicalSlug":"github-audit-agentdiet-dev-web-page-distiller-bm25-token-budget-9d6383e7"}