{"uid":"cap_twnquWj-4_FTbuG0g3u3k","slug":"whale-momentum-agentdiet-dev-web-url-markdown-distiller-with-bm25-ae694a1f","name":"Web URL Markdown 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/markdown-distill)","url":"https://whale-momentum.agentdiet.dev/v1/markdown-distill?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_sE8TPNYVA-fTyUBCV8gL3","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 webpage or raw HTML and distills it into compact, agent-ready Markdown, structured JSON, skeleton outline, or BM25-focused budget excerpt with token savings reporting","exampleAgentPrompt":"Distill the webpage at https://stripe.com/docs/payments into compact Markdown using budget mode, focusing on 'payment intents', and keep it under 500 tokens so it fits my context window.","exampleUseCases":[{"title":"Compress docs page for agent context","prompt":"Fetch https://docs.openai.com/api-reference and distill it into Markdown so I can include the key details in my agent's context without blowing the token limit."},{"title":"BM25 focused excerpt for research","prompt":"Pull the page at https://en.wikipedia.org/wiki/Retrieval-augmented_generation and extract only the parts about 'vector search' using budget mode, capped at 300 tokens."},{"title":"Structured JSON from product page","prompt":"Convert this product listing at https://www.apple.com/macbook-pro into structured JSON tables and metadata so my agent can parse the specs and pricing cleanly."}],"resultDescription":"Returns a JSON object containing distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), along with an roi_proof block showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved in USD. Also includes cache status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","HTML fetch blocked by target site (robots.txt, anti-bot measures)","max_tokens too low to produce meaningful output","BM25 query returns no relevant content within budget","Payment failure via x402 prevents execution","Malformed HTML input causes distillation failure"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read or reason about a webpage but must stay within a token budget, minimize LLM context costs, or receive structured/Markdown-formatted content rather than raw HTML. Especially useful when you need BM25-focused excerpt extraction (mode=budget with a query) to surface only the most relevant sections. Prefer over generic scraping endpoints when token efficiency and cost savings metrics are required.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:56.778Z","isFirstParty":false,"canonicalSlug":"whale-momentum-agentdiet-dev-web-url-markdown-distiller-with-bm25-ae694a1f"}