{"uid":"cap_alU3DEqznrZJ1FYwcv3N7","slug":"whale-momentum-agentdiet-dev-semantic-html-pruner-web-url-distiller-7376ea64","name":"Semantic HTML Pruner – Web URL Distiller","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/semantic-html-pruner)","url":"https://whale-momentum.agentdiet.dev/v1/semantic-html-pruner?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_M2BosbtL6B8AaCtfqlccF","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 compresses it into compact, agent-ready tokens using BM25 budget control and multiple distillation modes","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments into compact markdown, keeping it under 2000 tokens and focusing on the query 'payment intents' using budget mode?","exampleUseCases":[{"title":"Shrink docs page for LLM context","prompt":"Distill https://docs.anthropic.com/claude/overview into clean markdown and keep it under 1500 tokens — I need to fit it into my prompt without blowing my context window."},{"title":"Extract relevant section via BM25 query","prompt":"Pull https://openai.com/pricing and use budget mode with the query 'GPT-4o API cost' so I only get the pricing rows that matter, capped at 500 tokens."},{"title":"Structured table extraction from a webpage","prompt":"Fetch https://en.wikipedia.org/wiki/List_of_countries_by_GDP and distill it in structured mode so I get the tables and metadata in JSON format rather than raw HTML."}],"resultDescription":"Returns a distilled version of the webpage in the requested format (Markdown, structured JSON, skeleton outline, or BM25-focused excerpt), along with ROI proof metrics including raw token count, distilled token count, tokens saved, compression ratio, and estimated LLM cost saved. Also includes cache status and billing info.","failureModes":["Invalid or unreachable URL returns an error status","max_tokens set below minimum of 20 causes validation failure","BM25 query provided without mode=budget may be ignored","Raw HTML too large may hit processing limits","Payment/x402 authentication failure blocks the request"],"whenToPreferThis":"Choose this endpoint when you need to feed web page content into an LLM but want to minimize token usage and cost. It is especially useful when a target page has heavy boilerplate, navigation, or irrelevant sections, and you only need the semantically relevant portion. The BM25 budget mode makes it uniquely powerful when you have a specific query and a hard token ceiling. Prefer it over generic scrapers when token efficiency and LLM-readiness of output matter.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:44.933Z","isFirstParty":false,"canonicalSlug":"whale-momentum-agentdiet-dev-semantic-html-pruner-web-url-distiller-7376ea64"}