{"uid":"cap_GDGXTADlNeeqB8T-V-E6w","slug":"whale-momentum-agentdiet-dev-web-url-dom-distiller-bm25-budget-mode-d1b8cfa5","name":"Web URL DOM Distiller (BM25 Budget Mode)","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/dom-stripper)","url":"https://whale-momentum.agentdiet.dev/v1/dom-stripper?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_JbOiPrPLW8rtL5L4ATRu3","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 URL or raw HTML and distills it into compact, agent-ready tokens using Markdown, structured, skeleton, or BM25-focused budget modes","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments into clean Markdown and keep it under 1000 tokens, focusing on payment intents?","exampleUseCases":[{"title":"LLM context cost reduction for research","prompt":"Fetch https://en.wikipedia.org/wiki/Large_language_model and compress it into budget mode focused on 'training data' — cap it at 500 tokens so I don't blow my context window."},{"title":"Structured data extraction from pricing page","prompt":"Pull the pricing page at https://vercel.com/pricing and distill it in structured mode so I get the tables and metadata cleanly formatted for comparison."},{"title":"Skeleton outline of documentation site","prompt":"Give me a skeleton outline of https://docs.openai.com/api-reference so I can see the high-level structure without all the detailed content."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an ROI proof object showing raw token count, distilled token count, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and a compression ROI multiplier. Also includes cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 HTTP status — endpoint may return an error status","Raw HTML is malformed or too large to process within budget constraints","mode=budget used without a query parameter — BM25 ranking has no focus term","max_tokens set below 20 — rejected by schema validation","Target site blocks automated fetching (bot protection, Cloudflare) — returns empty or partial content","Payment failure via x402 — call blocked before execution"],"whenToPreferThis":"Choose this endpoint when you need to feed web page content into an LLM context and want to minimize token usage and cost. It is especially valuable when the target page is large, noisy, or HTML-heavy and you need clean Markdown, structured tables, or a BM25-ranked excerpt relevant to a specific query. Prefer it over generic scraping tools when token budget control and compression ROI measurement matter, or when working within strict LLM context window limits.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:22:42.763Z","isFirstParty":false,"canonicalSlug":"whale-momentum-agentdiet-dev-web-url-dom-distiller-bm25-budget-mode-d1b8cfa5"}