{"uid":"cap_xZQbQVtns0NsyqgX55F31","slug":"defi-yield-agentdiet-dev-web-distillation-with-bm25-budget-control-2b229ddf","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://defi-yield.agentdiet.dev/v1/docs-to-markdown)","url":"https://defi-yield.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_N0fDrqpK_K0pmaD2Rguhu","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"defi-yield.agentdiet.dev","brandSlug":"defi-yield-agentdiet-dev-mpp","brandBaseUrl":"https://defi-yield.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into Markdown, structured data, or a token-budget-capped BM25-ranked excerpt","exampleAgentPrompt":"Can you fetch the Stripe pricing page at https://stripe.com/pricing and distill it into clean Markdown, keeping it under 1000 tokens using budget mode with the query 'pricing tiers'?","exampleUseCases":[{"title":"LLM cost reduction for doc ingestion","prompt":"Pull the content from https://docs.openai.com/api-reference and compress it down to under 800 tokens in budget mode, focused on the query 'rate limits', so I can include it in my prompt without blowing up my token budget."},{"title":"Structured data extraction from webpage","prompt":"Grab https://example.com/product-specs and distill it in structured mode so I get back tables and metadata as JSON instead of raw HTML."},{"title":"Skeleton outline of a long article","prompt":"Take this raw HTML I have and give me a skeleton outline of it — just the headings and key structure — so I can quickly understand how the page is organized."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled output (Markdown text, structured JSON, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Also includes optional cache hit/miss status and billing metadata.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error status","Raw HTML is malformed and cannot be parsed — distillation may produce empty or degraded output","max_tokens set too low (below 20) — rejected by schema validation","mode=budget requested without a query parameter — BM25 ranking has no focus term","Target page blocks scraping via robots.txt or CAPTCHA — fetch fails","Payment not provided or insufficient — HTTP 402 returned"],"whenToPreferThis":"Choose this endpoint when you need to ingest web content into an LLM prompt and want to minimize token consumption via compression or BM25-ranked excerpting. Ideal for documentation ingestion, RAG pipelines, and any scenario where raw HTML is too verbose. Prefer over generic scrapers when you need built-in token budgeting, ROI reporting, or structured/skeleton output modes rather than raw HTML or unprocessed text.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:32:35.407Z","isFirstParty":false,"canonicalSlug":"defi-yield-agentdiet-dev-web-distillation-with-bm25-budget-control-9d15a7c2"}