{"uid":"cap_h_FE9t4XDKUbWyZonEm2o","slug":"whale-momentum-agentdiet-dev-semantic-html-pruner-with-bm25-budget-459a4404","name":"Semantic HTML Pruner 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/semantic-html-pruner)","url":"https://whale-momentum.agentdiet.dev/v1/semantic-html-pruner?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_cCJCmVBGLjTnRV53kHQ_4","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 and distills a URL or raw HTML into clean Markdown, structured JSON, skeleton outline, or a BM25-ranked token-budget excerpt for AI agents","exampleAgentPrompt":"Fetch the page at https://stripe.com/docs/payments and distill it into clean Markdown, keeping only the content relevant to 'payment intents', with a strict budget of 2000 tokens.","exampleUseCases":[{"title":"LLM-ready doc extraction for coding agent","prompt":"Grab the content from https://docs.anthropic.com/claude/reference and distill it into structured Markdown so I can feed it to my coding agent without blowing the context window."},{"title":"Token-budgeted research on competitor pricing","prompt":"Fetch https://www.salesforce.com/pricing/ and extract only the parts related to 'enterprise pricing tiers', keeping it under 1500 tokens — I need the structured layout, not all the marketing fluff."},{"title":"Page skeleton for navigation planning","prompt":"Pull https://github.com/openai/openai-python and give me a skeleton outline of the page structure so I can understand what sections exist before deciding which ones to read in full."}],"resultDescription":"Returns a JSON object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), a status field, an roi_proof block showing raw vs distilled token counts, compression ratio, and estimated LLM cost saved, plus optional cache hit/miss metadata and billing details.","failureModes":["Invalid or unreachable URL returns an error status","mode=budget without a query or max_tokens may return unfiltered output","Raw HTML that is too large may exceed processing limits","Payment failure via x402 returns HTTP 402 before processing","Paywalled or JavaScript-rendered pages may yield incomplete distillation","max_tokens set too low (below 20) is rejected by schema validation"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to consume web page content without exceeding LLM token limits — especially when BM25-ranked relevance filtering is needed to focus on a specific query topic. Prefer it over generic scrapers when compression ratio and cost savings need to be measurable, or when you need structured output modes (Markdown, JSON tables, skeleton) rather than raw HTML. Particularly valuable for agentic pipelines that process many pages and need ROI-provable token reduction.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:30:30.060Z","isFirstParty":false,"canonicalSlug":"whale-momentum-agentdiet-dev-semantic-html-pruner-with-bm25-budget-459a4404"}