{"uid":"cap_E_to77W_KQM8FZpDlMRB0","slug":"agentdiet-dev-agentdiet-url-to-markdown-distiller-with-bm25-budget-967cca96","name":"AgentDiet URL-to-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://agentdiet.dev/v1/url-to-markdown)","url":"https://agentdiet.dev/v1/url-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_rgryT-OXeNc7XTun13X5_","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"agentdiet.dev","brandSlug":"agentdiet-dev-mpp","brandBaseUrl":"https://agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into Markdown, structured JSON, skeleton outline, or a BM25-ranked token-budget excerpt to minimize LLM token consumption","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it into markdown using budget mode focused on the query 'payment intents', keeping it under 2000 tokens.","exampleUseCases":[{"title":"Token-efficient research on a documentation page","prompt":"Pull down https://docs.openai.com/api-reference and distill it into markdown using budget mode with the query 'function calling', capped at 1500 tokens — I want just the relevant parts without blowing my context."},{"title":"Structured data extraction from a product page","prompt":"Take this HTML I have from an e-commerce product page and distill it into structured JSON tables — pull out the product metadata, specs, and pricing sections."},{"title":"Skeleton outline of a long article","prompt":"Fetch https://www.nytimes.com/2024/01/15/technology/ai-regulation.html and give me a skeleton outline of the page so I can see the structure and headers without reading the whole thing."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown, structured tables, skeleton, 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 status and billing details.","failureModes":["URL is unreachable or returns non-200 — endpoint cannot fetch content","HTML payload is empty or malformed — distillation fails with no extractable content","max_tokens set below 20 — rejected by schema validation","BM25 query provided without mode=budget — query may be ignored","Rate limiting or payment failure via x402 — request rejected without billing"],"whenToPreferThis":"Choose this endpoint when you need to feed web content to an LLM but must control token costs — especially when you have a specific focus query (use budget+BM25 mode) or need structured extraction from arbitrary HTML. It is purpose-built for AI agent pipelines where raw HTML would be too large and token cost matters. Prefer it over generic scrapers when you need compression metrics (roi_proof) or when working within strict context window budgets.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:35:02.239Z","isFirstParty":false,"canonicalSlug":"agentdiet-dev-agentdiet-url-to-markdown-distiller-with-bm25-budget-967cca96"}