{"uid":"cap_7cSFGapUcnr2GV8OMhcjS","slug":"company-enrich-agentdiet-dev-web-url-to-compact-markdown-distiller-67bb7ee9","name":"Web URL to Compact Markdown Distiller (BM25 Budget Mode)","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://company-enrich.agentdiet.dev/v1/docs-to-markdown)","url":"https://company-enrich.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_O5QGjfvBPhor1H6dDBIXw","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"company-enrich.agentdiet.dev","brandSlug":"company-enrich-agentdiet-dev-mpp","brandBaseUrl":"https://company-enrich.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or raw HTML and distills it into compact, agent-ready Markdown, structured JSON, skeleton outline, or BM25-focused token-budgeted excerpts.","exampleAgentPrompt":"Grab the page at https://stripe.com/docs/api and distill it into compact markdown using budget mode with a focus query 'payment intents' and a max of 2000 tokens — I need a token-efficient version I can feed directly into my LLM.","exampleUseCases":[{"title":"Distill API docs for agent context","prompt":"Take the OpenAI API reference at https://platform.openai.com/docs/api-reference and distill it into structured markdown so I can include the key tables and metadata in my agent's context window without blowing my token budget."},{"title":"Budget-focused excerpt for RAG pipeline","prompt":"Distill https://docs.aws.amazon.com/s3/index.html in budget mode with the query 'bucket permissions' and cap it at 1500 tokens — I only want the most relevant content about S3 permissions for my retrieval pipeline."},{"title":"Convert raw HTML to skeleton outline","prompt":"I have some raw HTML from a competitor's pricing page — can you distill it into a skeleton outline so I can quickly see the structure and headings without reading through all the noise?"}],"resultDescription":"Returns a distilled version of the webpage or HTML in the chosen mode (Markdown, structured JSON with tables/metadata, skeleton outline, or BM25-ranked budget excerpt), along with an ROI proof object showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost savings. Also includes cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 — endpoint may return an error status","max_tokens set below 20 — rejected by schema validation","mode=budget used without a query parameter — BM25 ranking may be unfocused","HTML/URL contains no extractable text — returns minimal or empty data object","Payment not provided or insufficient — HTTP 402 response blocking execution","Invalid URL format — request fails input validation"],"whenToPreferThis":"Choose this endpoint when your agent needs to ingest web page content efficiently within a token budget — especially for LLM pipelines where raw HTML would be too verbose. It is ideal when you need Markdown for LLM readability, structured JSON tables for data extraction, a skeleton outline for navigation, or a BM25-ranked excerpt for retrieval-focused summarization. Prefer it over generic scrapers when token cost reduction and compression metrics matter, or when working with documentation pages like Stripe or AWS that need to fit in a constrained context window.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:24:35.719Z","isFirstParty":false,"canonicalSlug":"company-enrich-agentdiet-dev-web-url-to-compact-markdown-distiller-67bb7ee9"}