{"uid":"cap_Ldw-NByQB6FTCpE_mygYq","slug":"workflows-agentdiet-dev-webpage-distiller-bm25-budget-controlled-web-f0995cdd","name":"Webpage Distiller – BM25 Budget-Controlled Web Content Extraction","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://workflows.agentdiet.dev/v1/webpage-distiller)","url":"https://workflows.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_q2BEzbxOFKjd490s6CKbt","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"workflows.agentdiet.dev","brandSlug":"workflows-agentdiet-dev-mpp","brandBaseUrl":"https://workflows.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-controlled extraction modes","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments into compact markdown, keeping it under 800 tokens focused on the topic 'payment intents'?","exampleUseCases":[{"title":"Summarize competitor pricing page","prompt":"Distill https://www.competitor.com/pricing into structured tables so I can compare their plans — keep it under 600 tokens and focus on 'pricing tiers'."},{"title":"Extract docs content for agent context","prompt":"Fetch https://docs.openai.com/api-reference and distill it into skeleton mode so I get just the outline of available API endpoints without using up my whole context window."},{"title":"Compress raw HTML snippet","prompt":"I have a raw HTML blob from a news article — can you distill it into clean markdown and tell me how many tokens you saved compared to the original?"}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25 excerpt), alongside an 'roi_proof' block showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error status","Token budget (max_tokens) too small to produce meaningful content — may return truncated or empty data","BM25 query provided without mode=budget — query parameter may be silently ignored","Raw HTML payload too large — may exceed processing limits","Invalid URL format — validation error returned","Payment not fulfilled via x402 — 402 Payment Required response blocking execution"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web content but must control token spend — especially when working with long documentation pages, competitor sites, or any URL where raw content would overflow LLM context windows. It is preferable to generic scraping tools when BM25-focused relevance filtering or strict token budgets are needed, and superior to plain fetch when you need ROI proof (compression ratio, cost saved) alongside the content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:26:32.744Z","isFirstParty":false,"canonicalSlug":"workflows-agentdiet-dev-webpage-distiller-bm25-budget-controlled-web-f0995cdd"}