{"uid":"cap_m7W9G6fsz_oJZAtPFsPW5","slug":"token-intel-agentdiet-dev-html-to-markdown-distiller-with-bm25-budget-7596544c","name":"HTML 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://token-intel.agentdiet.dev/v1/html-to-markdown)","url":"https://token-intel.agentdiet.dev/v1/html-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_S_sR82iihifM2mCH6liyO","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"token-intel.agentdiet.dev","brandSlug":"token-intel-agentdiet-dev-mpp","brandBaseUrl":"https://token-intel.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or processes raw HTML and distills it into Markdown, structured JSON, skeleton outline, or a BM25-ranked token-budget excerpt","exampleAgentPrompt":"Fetch the page at https://stripe.com/docs/api and distill it into markdown with a strict budget of 2000 tokens, focusing on 'payment intents authentication' using BM25 mode so I only get the most relevant content.","exampleUseCases":[{"title":"Token-budget web research for LLM pipeline","prompt":"Pull the content from https://openai.com/research/gpt-4 and distill it down to at most 1500 tokens using budget mode with the query 'multimodal capabilities training data' — I need to feed it into my model without blowing my context window."},{"title":"Clean documentation page for RAG indexing","prompt":"Convert the HTML at https://docs.anthropic.com/claude/reference/messages-post into clean markdown so I can index it in my RAG system — use markdown mode and just give me the readable content without all the nav and footer noise."},{"title":"Structured data extraction from product page","prompt":"Take this raw HTML I'm pasting in and extract it in structured mode so I get the tables, metadata, and key fields as JSON — it's a product listing page and I need the specs in a machine-readable format."}],"resultDescription":"Returns a JSON object containing: the distilled content (Markdown string, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt) under 'data'; an 'roi_proof' object with raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd; optional cache metadata (HIT/MISS, latency_ms); optional billing info; and a status field ('ok').","failureModes":["Invalid or unreachable URL returns fetch error","Missing required 'url' field returns validation error","mode=budget without a 'query' or 'max_tokens' may return unfiltered or oversized content","Rate limiting or payment failure (HTTP 402) if USDC payment not completed","Raw HTML too large may cause timeout or truncation","Private/paywalled pages return empty or partial content","Malformed HTML may produce garbled markdown output"],"whenToPreferThis":"Choose this endpoint when you need to reduce token consumption before feeding web content to an LLM, especially with strict context budgets. It is uniquely suited for agents that must process arbitrary URLs at scale while controlling costs, thanks to BM25 relevance filtering and ROI metrics. Prefer it over generic scrapers when you want distilled, LLM-ready output rather than raw HTML, and when you need structured or skeleton modes beyond plain text extraction.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:30:52.664Z","isFirstParty":false,"canonicalSlug":"token-intel-agentdiet-dev-html-to-markdown-distiller-with-bm25-budget-7596544c"}