{"uid":"cap_z9ztnTNbGII_7iQKedG8E","slug":"defi-yield-agentdiet-dev-webpage-distiller-bm25-budgeted-web-content-fec6721b","name":"Webpage Distiller – BM25-Budgeted Web Content to Agent Tokens","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://defi-yield.agentdiet.dev/v1/webpage-distiller)","url":"https://defi-yield.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_VewVDOpozf8W0vOP39d94","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"defi-yield.agentdiet.dev","brandSlug":"defi-yield-agentdiet-dev-mpp","brandBaseUrl":"https://defi-yield.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or processes raw HTML and distills it into compact, agent-ready tokens using configurable extraction modes and BM25 budget control","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into compact markdown — use budget mode with the query 'payment intents API' and cap it at 1000 tokens so I can feed it into my LLM without blowing the context window.","exampleUseCases":[{"title":"LLM cost-saving doc summarization","prompt":"Grab https://docs.openai.com/api-reference and distill it down to under 800 tokens using budget mode, focused on the query 'chat completions endpoint', so I can include only the relevant bits in my prompt."},{"title":"Structured data extraction from a landing page","prompt":"Fetch https://www.anthropic.com/claude and distill it in structured mode so I get JSON tables and metadata — I want to pull out product features and pricing info cleanly."},{"title":"Skeleton outline of a research article","prompt":"Distill https://arxiv.org/abs/2305.10601 in skeleton mode so I just get the heading outline and section structure without all the body text."}],"resultDescription":"Returns a JSON object containing: the distilled content (Markdown, structured JSON, skeleton outline, or BM25-ranked excerpt depending on mode), a cache status object (HIT/MISS with latency), billing details, and an roi_proof block showing raw vs. distilled token counts, tokens saved, compression ratio percentage, ROI multiplier, and estimated LLM cost saved in USD.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error status","URL points to a non-HTML resource (PDF, binary) — distillation may fail or return empty","max_tokens set too low — output may be truncated or query may not be satisfiable within budget","Raw HTML input is malformed — structured mode may produce incomplete tables","Payment not included or insufficient — HTTP 402 returned blocking the response","Rate limits or network timeouts on the target URL — fetch step fails before distillation"],"whenToPreferThis":"Choose this endpoint when you need to fetch and compress a web page's content before passing it to an LLM, especially when token budget is a concern. It is ideal for agents that need to read arbitrary URLs at scale without burning large token budgets, or when you want BM25-ranked relevance filtering to focus the output on a specific query. Prefer it over raw scraping tools when you need the output to already be cleaned, tokenized, and cost-quantified.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:42.650Z","isFirstParty":false,"canonicalSlug":"defi-yield-agentdiet-dev-webpage-distiller-bm25-budgeted-web-content-fec6721b"}