{"uid":"cap_70ajvzfbfnr-c-Sh-wzL8","slug":"token-intel-agentdiet-dev-html-url-to-markdown-distiller-with-bm25-75478cb4","name":"HTML/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://token-intel.agentdiet.dev/v1/html-to-markdown)","url":"https://token-intel.agentdiet.dev/v1/html-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_TBQ20HsNNVmmcEeSRKaPk","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 accepts raw HTML and distills it into compact, agent-ready Markdown or structured output with token-budget enforcement via BM25 ranking","exampleAgentPrompt":"Fetch the page at https://docs.stripe.com/payments and distill it into compact markdown using budget mode, focused on 'payment intents', capped at 500 tokens.","exampleUseCases":[{"title":"LLM cost reduction via web compression","prompt":"Pull the content from https://openai.com/pricing and compress it into markdown with a 300-token budget focused on 'API pricing tiers' — I want to minimize what I send to the LLM."},{"title":"Skeleton outline for research navigation","prompt":"Fetch https://en.wikipedia.org/wiki/Large_language_model and give me just a skeleton outline of the page structure so I can decide which sections to drill into."},{"title":"Structured data extraction from a product page","prompt":"Distill https://www.apple.com/iphone into structured mode so I can get the tables and metadata as clean JSON for my product comparison agent."}],"resultDescription":"Returns a JSON object with distilled content (Markdown text, structured JSON tables/metadata, page skeleton, or BM25-ranked budget excerpt), plus an ROI proof block showing raw vs distilled token counts, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and a cache hit/miss indicator.","failureModes":["Invalid or unreachable URL returns an error status","max_tokens below minimum of 20 triggers validation error","mode=budget without a query may return unranked content","Raw HTML injection via the html field may produce unexpected output if malformed","Payment failure via x402 returns HTTP 402 with no content","Rate limits or bot-blocking on target URLs may return empty or partial content"],"whenToPreferThis":"Choose this endpoint when your agent needs to fetch live web content and must stay within a strict token budget before passing content to an LLM. It is especially valuable when the target page is large and you want BM25-ranked relevance filtering, or when you need structured tables/metadata extracted from HTML rather than raw text. Prefer it over generic web scrapers when token cost savings and ROI measurement matter to your pipeline.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:22:48.050Z","isFirstParty":false,"canonicalSlug":"token-intel-agentdiet-dev-html-url-to-markdown-distiller-with-bm25-75478cb4"}