{"uid":"cap_3oNoyW8fzbMvFv1Jdk9fX","slug":"company-enrich-agentdiet-dev-webpage-distiller-with-bm25-budget-control-4694751e","name":"Webpage 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://company-enrich.agentdiet.dev/v1/webpage-distiller)","url":"https://company-enrich.agentdiet.dev/v1/webpage-distiller?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_1yN8-k4eJYZhaDW3SBuek","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"company-enrich.agentdiet.dev","brandSlug":"company-enrich-agentdiet-dev-mpp","brandBaseUrl":"https://company-enrich.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into compact Markdown, structured JSON, skeleton outline, or BM25-ranked token-budget excerpt","exampleAgentPrompt":"Distill the page at https://stripe.com/docs/payments/payment-intents into clean markdown using budget mode, focused on 'payment intent lifecycle', and keep it under 800 tokens.","exampleUseCases":[{"title":"LLM context-window-safe doc reading","prompt":"Fetch https://docs.openai.com/api-reference/chat and distill it into budget mode, focused on 'chat completions parameters', capped at 1000 tokens so it fits in my context window."},{"title":"Structured table extraction from a pricing page","prompt":"Grab the HTML from our competitor's pricing page at https://example.com/pricing and distill it in structured mode so I can pull out all the plan names and prices as JSON."},{"title":"Skeleton outline for research triage","prompt":"Distill https://arxiv.org/abs/2310.06825 in skeleton mode so I can see the section headings and decide which parts of the paper are worth reading in full."}],"resultDescription":"Returns a 'data' object containing the distilled content in the chosen format (Markdown, structured JSON tables/metadata, skeleton outline, or BM25 budget excerpt), along with an 'roi_proof' block detailing raw vs distilled token counts, tokens saved, compression ratio percentage, ROI multiplier, and estimated LLM cost saved in USD. Also includes optional cache status (HIT/MISS), billing information, and execution status.","failureModes":["URL is unreachable or returns non-200 (network error or timeout)","HTML payload is empty or malformed beyond parsing","mode=budget used without a query field (BM25 requires a focus query)","max_tokens set below 20 (minimum ceiling enforced)","Target page is behind authentication or bot-detection (returns blocked/empty content)","Payment not attached or insufficient (HTTP 402 returned)"],"whenToPreferThis":"Choose this endpoint when you need to read a webpage but must control token consumption — especially useful when feeding web content into an LLM with a limited context window. It is the right choice over raw fetch-and-parse when you want BM25-ranked relevance trimming (budget mode), clean Markdown output without HTML bloat, or structured JSON tables extracted from page content. Prefer it over generic scrapers when ROI/token-savings reporting matters to your agent pipeline.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:31:22.066Z","isFirstParty":false,"canonicalSlug":"company-enrich-agentdiet-dev-webpage-distiller-with-bm25-budget-control-4694751e"}