{"uid":"cap_qzbchOwUi7ZNEsahCh6JE","slug":"domain-osint-agentdiet-dev-web-distillation-with-bm25-budget-control-53eca6e8","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://domain-osint.agentdiet.dev/v1/docs-to-markdown)","url":"https://domain-osint.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_XuJDq7lfaWPiLNHmQZ8Xr","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"domain-osint.agentdiet.dev","brandSlug":"domain-osint-agentdiet-dev-mpp","brandBaseUrl":"https://domain-osint.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts 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 with a 2000-token budget, focused on the query 'payment intents', so I can feed just the relevant parts to my LLM.","exampleUseCases":[{"title":"Token-budget documentation summarization","prompt":"Grab the content at https://docs.openai.com/api-reference and distill it into a BM25-focused excerpt under 1500 tokens using the query 'function calling', so I can pass only the relevant section to my model."},{"title":"Structured data extraction from webpage","prompt":"Fetch https://example.com/pricing and convert it to structured JSON tables so I can parse the pricing tiers programmatically."},{"title":"Clean markdown from raw HTML","prompt":"I have this raw HTML from a scraped article — can you distill it into clean, readable markdown and give me a skeleton outline of the headings?"}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled output (Markdown, structured JSON, skeleton, or BM25 excerpt), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd. Also includes cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns an error status","HTML too large may exceed processing limits","BM25 budget mode requires both 'query' and 'max_tokens' to produce meaningful results","Missing required 'url' field returns a validation error","Rate limiting or payment failure via x402 may block the request"],"whenToPreferThis":"Choose this endpoint when you need to feed web content to an LLM and want to minimize token usage through intelligent compression. It is especially useful when you have a specific query and want BM25-ranked excerpts rather than full-page content, or when you need structured JSON tables or a skeleton outline instead of raw HTML. Prefer it over generic scrapers when token cost reduction and ROI metrics matter.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:37:13.422Z","isFirstParty":false,"canonicalSlug":"domain-osint-agentdiet-dev-web-distillation-with-bm25-budget-control-04fd791d"}