{"uid":"cap_4eXZdNDc0j9p5kHA2O-iY","slug":"whale-momentum-agentdiet-dev-web-url-distiller-with-bm25-budget-control-0d63b48b","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://whale-momentum.agentdiet.dev/v1/web-scrape)","url":"https://whale-momentum.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_G-oeD8GVsyNFpiekc2FNF","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"whale-momentum.agentdiet.dev","brandSlug":"whale-momentum-agentdiet-dev-mpp","brandBaseUrl":"https://whale-momentum.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a web URL (or accepts raw HTML) and distills it into compact, agent-ready tokens using markdown, structured, skeleton, or BM25 budget modes","exampleAgentPrompt":"Fetch the page at https://docs.stripe.com/payments and distill it into compact markdown, keeping only the most relevant content under 500 tokens using budget mode with the query 'payment intents'.","exampleUseCases":[{"title":"Token-budget research for agent context","prompt":"Grab https://en.wikipedia.org/wiki/Large_language_model and distill it down to no more than 300 tokens in budget mode, focused on the query 'training data'."},{"title":"Structured data extraction from product page","prompt":"Scrape https://www.apple.com/iphone/ and return the content as structured JSON tables — I want product specs and pricing organized neatly."},{"title":"Skeleton outline of a long article","prompt":"Fetch https://www.paulgraham.com/startupideas.html and give me just the skeleton outline so I can see the main sections without reading the whole thing."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (markdown text, structured JSON, skeleton outline, or BM25 budget excerpt depending on mode), plus an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Also includes cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","Token budget too low (max_tokens < 20) returns a validation error","Raw HTML provided with a URL may cause conflicts","BM25 query missing when mode=budget may return unfiltered content","Payment failure via x402 blocks the request","Rate limiting or anti-scraping measures on target site may cause fetch failures","Unsupported mode enum value returns a bad request error"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest a live webpage but must stay within a token budget — especially useful when the raw page is too large for an LLM context window. The BM25 budget mode makes it uniquely suited for targeted extraction around a specific query. Prefer over generic scrapers when you need built-in compression metrics and ROI proof of token savings. Also useful when you already have raw HTML and want structured or skeleton output without an additional fetch.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:39.350Z","isFirstParty":false,"canonicalSlug":"whale-momentum-agentdiet-dev-web-url-distiller-with-bm25-budget-control-0d63b48b"}