{"uid":"cap_40BDxS4iVX81B__JJ33fs","slug":"whale-momentum-agentdiet-dev-html-url-distiller-with-bm25-budget-5b73ecd7","name":"HTML/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/clean-html)","url":"https://whale-momentum.agentdiet.dev/v1/clean-html?utm_source=zero.xyz","method":"POST","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__-DbigOKZmdMBr9khx8nX","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 accepts raw HTML and distills it into clean Markdown, structured JSON, an outline skeleton, or a BM25-ranked token-budget excerpt","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments into clean markdown using budget mode, focused on 'payment intents', and cap it at 2000 tokens so it fits in my context window.","exampleUseCases":[{"title":"LLM context-window compression for docs","prompt":"Fetch the React documentation at https://react.dev/reference/react/useState and distill it into markdown with a 1500 token ceiling, focused on the query 'useState hook examples', so I can pass it to my LLM without hitting the context limit."},{"title":"Structured table extraction from pricing page","prompt":"Pull the pricing page at https://vercel.com/pricing and distill it in structured mode so I get all the plan tiers, prices, and feature rows as JSON tables I can compare programmatically."},{"title":"Skeleton outline of a long article","prompt":"I have this raw HTML from a news article — can you distill it in skeleton mode to give me just the headline, section headings, and subheadings so I can decide if it's worth reading in full?"}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), along with an 'roi_proof' block showing raw vs distilled token counts, tokens saved, compression ratio percentage, LLM cost saved in USD, and ROI multiplier. Also includes optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 — fetch fails with error status","HTML payload is empty or malformed — distillation returns minimal or empty data","max_tokens is set below 20 — validation error","mode=budget used without a query parameter — BM25 ranking has no focus term","Payment not provided or insufficient — HTTP 402 payment required response","URL is behind authentication/paywall — content may be incomplete or inaccessible","Very large pages may time out before distillation completes"],"whenToPreferThis":"Choose this endpoint when you need to reduce token overhead before passing web content to an LLM — especially when you want BM25-ranked relevance filtering against a specific query. It is preferable to generic scraping APIs when token budget control matters, when you need multiple output modes (Markdown, structured, skeleton), or when you want built-in ROI metrics showing exactly how many tokens and dollars were saved. Ideal for agentic pipelines where context window space is a constraint.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:31:00.482Z","isFirstParty":false,"canonicalSlug":"whale-momentum-agentdiet-dev-html-url-distiller-with-bm25-budget-5b73ecd7"}