{"uid":"cap_4P8jGDSIxIaYSbbbkAVO_","slug":"github-audit-agentdiet-dev-web-url-to-markdown-distiller-with-bm25-2bef4165","name":"Web 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://github-audit.agentdiet.dev/v1/docs-to-markdown)","url":"https://github-audit.agentdiet.dev/v1/docs-to-markdown?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_zHipVA05wVkxo_Q13kwOG","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"github-audit.agentdiet.dev","brandSlug":"github-audit-agentdiet-dev-mpp","brandBaseUrl":"https://github-audit.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a web URL or raw HTML and converts it into compact, token-efficient markdown or structured output using configurable distillation modes and BM25-based token budgeting","exampleAgentPrompt":"Can you fetch the Stripe docs page at https://stripe.com/docs/api/charges and distill it into compact markdown with a 2000 token budget, focusing on the 'authentication' topic?","exampleUseCases":[{"title":"Compress API docs for LLM context","prompt":"Grab the OpenAI API reference at https://platform.openai.com/docs/api-reference and distill it into markdown — I only have about 3000 tokens to spare, so use budget mode with 'rate limits' as the focus query."},{"title":"Extract structured tables from a product page","prompt":"Pull the pricing page at https://www.anthropic.com/pricing and extract it in structured mode so I get the pricing tiers as JSON tables I can reason over."},{"title":"Outline a long technical document","prompt":"Fetch https://docs.python.org/3/library/asyncio.html and give me a skeleton outline of the page structure — just the headings and section summaries, nothing more."}],"resultDescription":"Returns a distilled version of the webpage in the requested mode (markdown, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt), along with ROI proof metrics including raw vs distilled token counts, compression ratio percentage, tokens saved, ROI multiplier, and estimated LLM cost saved. Also includes cache status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","max_tokens below minimum of 20 is rejected","BM25 query with no matching content may return minimal excerpt","Raw HTML input that is malformed may produce poor distillation quality","Rate limiting or payment failure via x402 may block the call"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read or process web content but must stay within a token budget, when you need structured or outline-form extraction from arbitrary URLs, or when you want to measure and minimize LLM token costs from web content. Prefer it over generic scrapers when BM25 relevance filtering or multiple distillation modes (markdown, structured, skeleton, budget) are required.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:47:47.712Z","isFirstParty":false,"canonicalSlug":"github-audit-agentdiet-dev-web-url-to-markdown-distiller-with-bm25-0bf90a68"}