{"uid":"cap_eFKCEulCnKaz6mOyArWXO","slug":"company-enrich-agentdiet-dev-web-distillation-with-bm25-budget-control-ae347b3e","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/docs-to-markdown)","url":"https://company-enrich.agentdiet.dev/v1/docs-to-markdown?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_LjMS5_3tcFwtrxWOVVx0D","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 accepts raw HTML and converts it to clean Markdown, structured JSON, or a BM25-ranked token-budget excerpt for LLM consumption.","exampleAgentPrompt":"Fetch the page at https://stripe.com/docs/payments/payment-intents and distill it to markdown, but cap it at 2000 tokens and focus the BM25 budget on 'payment confirmation webhooks'.","exampleUseCases":[{"title":"Token-budget docs extraction for agent","prompt":"Pull the Stripe documentation page at https://stripe.com/docs/api/charges and give me only the parts about 'refund handling' — keep it under 1500 tokens using budget mode."},{"title":"Clean markdown from raw HTML paste","prompt":"I have this raw HTML blob from a company's pricing page — can you distill it into clean markdown so I can feed it to my LLM without all the nav and footer noise?"},{"title":"Structured JSON tables from a webpage","prompt":"Go to https://en.wikipedia.org/wiki/List_of_S%26P_500_companies and extract the data as structured JSON tables rather than raw markdown."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown string, structured JSON, skeleton outline, or BM25 excerpt depending on mode), an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd, plus optional cache hit/miss info and billing details.","failureModes":["URL is unreachable or returns non-200 — endpoint may return an error status","HTML payload is empty or malformed — distillation may produce empty output","Token budget too low (below 20) — rejected by schema validation","BM25 query missing when mode=budget — may fall back to default mode or return error","Rate limit or payment failure via x402 — 402 response requiring payment","Target page is JavaScript-rendered SPA — fetched HTML may lack meaningful content"],"whenToPreferThis":"Choose this endpoint when you need to feed webpage or HTML content to an LLM and want to minimize token consumption, especially when you have a specific topic focus (use mode=budget with a BM25 query) or need structured extraction. It is preferable over raw scraping when token cost and context window size matter, and over generic summarization APIs when you need deterministic compression ratios and ROI proof. Particularly useful for agent pipelines consuming documentation, news, or research pages at scale.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:37:30.679Z","isFirstParty":false,"canonicalSlug":"company-enrich-agentdiet-dev-web-distillation-with-bm25-budget-control-2d03f821"}