{"uid":"cap_Vn69RYdqp1alJantZ5Uae","slug":"whale-momentum-agentdiet-dev-web-url-distiller-with-bm25-budget-control-503f557f","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/spa-markdown-reader)","url":"https://whale-momentum.agentdiet.dev/v1/spa-markdown-reader?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_I0FY97NjolJ8qpnjdqEDE","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 Markdown, structured JSON, skeleton outline, or BM25-focused excerpt with token compression metrics.","exampleAgentPrompt":"Distill https://docs.stripe.com/payments/accept-a-payment into compact Markdown using budget mode, focused on 'accept payment integration', with a max of 500 tokens.","exampleUseCases":[{"title":"Stripe docs extraction for coding agent","prompt":"Pull the Stripe payment intents docs at https://docs.stripe.com/api/payment_intents and distill them into structured Markdown so I can pass just the relevant parts to my coding agent without blowing my token budget."},{"title":"Research page summarization with token cap","prompt":"Fetch https://arxiv.org/abs/2310.06825 and give me a skeleton outline of the paper — I only want the section headers and key takeaways, keep it under 300 tokens."},{"title":"Competitor pricing page focused extraction","prompt":"Go to https://openai.com/pricing and extract only the content related to 'GPT-4o token pricing' using budget mode with a 400-token ceiling — I want to compare costs without reading the whole page."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown text, structured JSON tables, skeleton outline, or BM25-focused 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. Optionally includes cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 HTTP status — endpoint may return an error status","Provided HTML string is malformed or empty — distillation may return minimal output","max_tokens set below minimum of 20 — rejected with validation error","mode=budget requested without a query parameter — BM25 scoring may default to full extraction","JavaScript-heavy SPAs may not render fully, resulting in sparse distilled content","Payment not processed (HTTP 402) if x402 credentials are missing or insufficient"],"whenToPreferThis":"Choose this endpoint when you need to feed web content to an LLM but want to minimize token usage — especially for documentation pages, research articles, or competitor sites where only a portion is relevant. The BM25 budget mode makes it uniquely suited for query-focused extraction with a strict token ceiling, distinguishing it from generic scrapers that return raw HTML or full-page Markdown without compression accounting.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:43.425Z","isFirstParty":false,"canonicalSlug":"whale-momentum-agentdiet-dev-web-url-distiller-with-bm25-budget-control-0d63b48b"}