{"uid":"cap_WC0XQ6eKny43Yj7eMpn8M","slug":"company-enrich-agentdiet-dev-web-distillation-with-bm25-budget-control-2d03f821","name":"Web Distillation 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/pdf-extract)","url":"https://company-enrich.agentdiet.dev/v1/pdf-extract?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_0Ei6rOu6oyKTDIoA-z8KW","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 a URL or processes raw HTML and distills it into clean Markdown, structured JSON, skeleton outline, or a BM25-ranked token-budgeted excerpt","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it into clean markdown, keeping a strict budget of 2000 tokens focused on the query 'payment intents API'.","exampleUseCases":[{"title":"Trim docs page for LLM context","prompt":"Grab https://docs.openai.com/api-reference and distill it down to a 1500-token budget in budget mode, focused on the query 'function calling', so I can feed just the relevant parts to my model."},{"title":"Convert competitor landing page to structured data","prompt":"Take the raw HTML from Salesforce's pricing page and distill it into structured JSON tables so I can compare their pricing tiers programmatically."},{"title":"Outline a long article for quick review","prompt":"Fetch https://en.wikipedia.org/wiki/Large_language_model and give me a skeleton outline of the page structure so I can see the main sections at a glance."}],"resultDescription":"Returns a data object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an roi_proof object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes optional cache hit/miss status and billing details.","failureModes":["URL unreachable or returns non-200 status — endpoint may return an error status","HTML content too large to process within limits","Invalid or missing URL field — request rejected with validation error","BM25 budget mode used without a query parameter — may produce degraded results","Token budget ceiling set below minimum of 20 — rejected","Rate limiting or payment failure via x402 — 402 response requiring payment"],"whenToPreferThis":"Choose this endpoint when you need to reduce the token footprint of web content before passing it to an LLM, especially when you have a strict context window budget or want to extract only the most relevant sections via BM25 query scoring. Ideal for agentic pipelines that need to read many web pages without blowing LLM token costs. Prefer over raw fetch-and-parse when compression ratio, structured extraction, or budget control matters.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:36:01.152Z","isFirstParty":false,"canonicalSlug":"company-enrich-agentdiet-dev-web-distillation-with-bm25-budget-control-2d03f821"}