{"uid":"cap_9DPXbOZlJ56Zy7KWUEapY","slug":"whale-momentum-agentdiet-dev-web-url-distiller-with-bm25-budget-control-bcd6cd13","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/paywall-clean-extract)","url":"https://whale-momentum.agentdiet.dev/v1/paywall-clean-extract?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_DJJkFP3XoqY3v4F9pxsvJ","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 tokens using markdown, structured, skeleton, or BM25 budget-controlled extraction modes","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/payments/quickstart and distill it into clean markdown, keeping it under 1500 tokens and focusing on anything related to payment intents?","exampleUseCases":[{"title":"Budget-aware doc extraction for agent","prompt":"Grab https://docs.openai.com/api-reference and distill it into budget mode with a max of 800 tokens, focused on the query 'streaming chat completions' — I need only the most relevant bits for my agent."},{"title":"Structured table extraction from pricing page","prompt":"Pull https://aws.amazon.com/ec2/pricing/ and extract it in structured mode so I get the pricing tables as clean JSON — I want to compare instance costs programmatically."},{"title":"Skeleton outline of a long article","prompt":"Take this URL https://en.wikipedia.org/wiki/Large_language_model and give me a skeleton outline of the whole page so I can see the high-level structure before deciding which section to dig into."}],"resultDescription":"Returns a distilled representation of the target webpage in the requested format (markdown, structured JSON, skeleton outline, or BM25-ranked budget excerpt), along with ROI proof metrics including 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","Paywalled or bot-blocked pages may return incomplete or empty content","mode=budget without a query or max_tokens may return unfiltered output","Very large pages may hit internal limits before reaching the token ceiling","HTML injection via the html parameter with malformed markup may cause parse errors","Payment failure via x402 prevents call completion"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read web content but must stay within a token budget, minimize LLM inference costs, or receive pre-cleaned content rather than raw HTML. Ideal when the target page is long, noisy, or ad-heavy and you want structured or markdown output. Prefer the budget+BM25 mode when only a specific topic within a large page is relevant. Use over generic scrapers when token efficiency and ROI metrics matter.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:44.110Z","isFirstParty":false,"canonicalSlug":"whale-momentum-agentdiet-dev-web-url-distiller-with-bm25-budget-control-0d63b48b"}