{"uid":"cap_psyYbb4Vzpi6gaHboa9gz","slug":"defi-yield-agentdiet-dev-web-url-distiller-with-bm25-budget-control-fd335355","name":"Web URL 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://defi-yield.agentdiet.dev/v1/web-scrape)","url":"https://defi-yield.agentdiet.dev/v1/web-scrape?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_VFyhlzboX2WFz4NWOLLDV","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 webpage (or accepts raw HTML) and distills it into compact, agent-ready tokens using configurable extraction modes including BM25-focused budget trimming","exampleAgentPrompt":"Can you fetch the content at https://docs.stripe.com/api and distill it into compact markdown, keeping it under 2000 tokens and focusing on the authentication section?","exampleUseCases":[{"title":"Distill docs page for agent context","prompt":"Grab the content from https://platform.openai.com/docs/guides/function-calling and distill it into markdown — I want to feed it to my agent without burning through my token budget."},{"title":"BM25-focused budget scrape for research","prompt":"Fetch https://en.wikipedia.org/wiki/Ethereum and extract only the parts most relevant to 'proof of stake consensus mechanism', keeping the output under 500 tokens in budget mode."},{"title":"Structured data extraction from landing page","prompt":"Scrape https://stripe.com/pricing and return the content in structured mode so I can get the pricing tiers and feature tables as clean JSON."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-trimmed excerpt depending on mode), plus ROI proof metrics (raw tokens, distilled tokens, tokens saved, compression ratio percentage, LLM cost saved in USD, ROI multiplier), optional cache hit/miss status with latency, and billing details.","failureModes":["URL is unreachable or returns non-200 HTTP status — endpoint may return an error status","URL is paywalled or bot-protected (e.g. Cloudflare) — content may be empty or partial","max_tokens set too low (below 20) — rejected by schema validation","Invalid mode value supplied — rejected by enum validation","HTML payload too large — may time out or be truncated","Payment (x402) not completed — request blocked before processing"],"whenToPreferThis":"Choose this endpoint when you need to feed live web content to an LLM but want to minimize token consumption and cost — especially when you need BM25-relevance filtering to focus on a specific subtopic within a large page, or when you want structured/skeleton extraction rather than raw HTML. Prefer it over generic scraping tools when token budget control and ROI transparency (tokens saved, compression ratio) matter to your agent pipeline.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:39.000Z","isFirstParty":false,"canonicalSlug":"defi-yield-agentdiet-dev-web-url-distiller-with-bm25-budget-control-fd335355"}