{"uid":"cap_D4TLrtmAuGSmDdT_VpwX-","slug":"domain-osint-agentdiet-dev-web-url-markdown-distiller-with-bm25-7b575552","name":"Web URL Markdown 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://domain-osint.agentdiet.dev/v1/markdown-distill)","url":"https://domain-osint.agentdiet.dev/v1/markdown-distill?utm_source=zero.xyz","method":"GET","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_tPtsPMndDy65yvOuTidaD","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 web URL or raw HTML and distills it into compact, agent-ready Markdown, structured JSON, skeleton outline, or BM25-focused token budget excerpt","exampleAgentPrompt":"Distill the content at https://docs.stripe.com/api into compact markdown using budget mode, focused on 'payment intents', and keep it under 500 tokens.","exampleUseCases":[{"title":"LLM cost reduction before summarization","prompt":"Pull the page at https://techcrunch.com/2025/06/01/openai-raises-billions and compress it into markdown mode so I'm only passing the essential content to my summarizer — show me how many tokens you saved."},{"title":"Budget-capped research query","prompt":"Fetch https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) in budget mode with the query 'attention mechanism' and a max of 300 tokens — I only want the most relevant excerpt."},{"title":"Structured data extraction from product page","prompt":"Distill https://www.apple.com/iphone-16-pro/ in structured mode so I get the specs and pricing as JSON tables rather than raw HTML."}],"resultDescription":"Returns a 'data' object containing distilled content in the requested format (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused budget excerpt), plus an 'roi_proof' object showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost savings. Optionally includes cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","Missing required 'url' parameter causes a 400-level error","mode=budget without a 'query' parameter may produce unfocused results","max_tokens below minimum of 20 is rejected","Raw HTML too large may time out or exceed processing limits","Payment not provided or insufficient triggers HTTP 402"],"whenToPreferThis":"Choose this endpoint when you need to feed web page content into an LLM but want to minimize token usage and cost. It is especially valuable when operating under strict context window constraints, when you need BM25-ranked relevance filtering to surface only query-relevant passages, or when you want structured/skeleton extraction rather than raw HTML. Prefer it over generic web scrapers when token efficiency and LLM-readiness are priorities.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:24.609Z","isFirstParty":false,"canonicalSlug":"domain-osint-agentdiet-dev-web-url-markdown-distiller-with-bm25-7b575552"}