{"uid":"cap_yEY9tO0eOiHMybcbGHUct","slug":"agentdiet-dev-webpage-distiller-with-bm25-budget-control-3906b04b","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://agentdiet.dev/v1/webpage-distiller)","url":"https://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_mgrMxEdjCGVlnmGSxOxSV","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"agentdiet.dev","brandSlug":"agentdiet-dev-mpp","brandBaseUrl":"https://agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into compressed Markdown, structured JSON, skeleton outline, or BM25-focused excerpts within a strict token budget","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments/payment-intents and distill it in budget mode focused on the query 'webhook event handling', keeping it under 800 tokens.","exampleUseCases":[{"title":"Fitting docs into agent context","prompt":"Grab the OpenAI API reference page at https://platform.openai.com/docs/api-reference and distill it into Markdown, keeping it under 1000 tokens focused on 'function calling'."},{"title":"Structured table extraction from webpage","prompt":"Pull https://en.wikipedia.org/wiki/List_of_countries_by_GDP and distill it in structured mode so I get the tables and metadata as clean JSON."},{"title":"Skeleton outline for research triage","prompt":"Distill https://arxiv.org/abs/2405.00001 in skeleton mode so I can see the section headings and decide if it's worth reading in full."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt), alongside an ROI proof block showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Also includes cache status (HIT/MISS) and billing details.","failureModes":["URL is unreachable or returns non-200 status — fetch failure error","HTML payload is empty or malformed — parse error","max_tokens set too low (below 20) — validation error rejected by schema","mode=budget used without a query field — may return unguided excerpt","Rate limit or payment failure via x402 — 402 Payment Required response","Target site blocks crawlers — may return empty or partial content"],"whenToPreferThis":"Use this endpoint when an AI agent needs to consume web content that would otherwise overflow its context window, or when you need BM25-ranked relevance filtering to extract only the portions of a page relevant to a specific query. It is especially valuable over raw fetch-and-pass approaches when token cost and context efficiency matter. Prefer the budget mode for precise token-ceiling enforcement, structured mode when you need tabular or metadata extraction, and skeleton mode for fast triage of long documents.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:37:31.086Z","isFirstParty":false,"canonicalSlug":"agentdiet-dev-webpage-distiller-with-bm25-budget-control-3906b04b"}