{"uid":"cap_TcfJz1rHxLmNxOA8ecqdN","slug":"sec-intel-agentdiet-dev-url-html-markdown-distiller-with-bm25-budget-b3fa721b","name":"URL & HTML 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://sec-intel.agentdiet.dev/v1/markdown-distill)","url":"https://sec-intel.agentdiet.dev/v1/markdown-distill?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_J21ssWYB4qsk0fPD9qXAs","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"sec-intel.agentdiet.dev","brandSlug":"sec-intel-agentdiet-dev-mpp","brandBaseUrl":"https://sec-intel.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML payload into clean Markdown, structured JSON, skeleton outline, or a BM25-ranked token-budgeted excerpt","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/payments and distill it into clean markdown using budget mode, focused on 'payment intents', keeping it under 2000 tokens?","exampleUseCases":[{"title":"LLM-ready webpage compression","prompt":"Grab https://openai.com/pricing and distill it into structured markdown so I can feed it to my model — I want the tables and metadata, not all the nav and footer junk."},{"title":"Token-budgeted research excerpt","prompt":"Distill https://en.wikipedia.org/wiki/Retrieval-augmented_generation into a BM25 budget excerpt focused on 'vector databases', keeping it under 500 tokens — I'm trying to fit it into a tight context window."},{"title":"Raw HTML cleanup for AI pipeline","prompt":"I have a raw HTML blob from a scraped product page — can you distill it into clean markdown so I can pass it to my summarization agent without blowing the token limit?"}],"resultDescription":"Returns a JSON object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), along with ROI proof metrics (raw vs distilled token counts, compression ratio, estimated LLM cost saved), cache status (HIT/MISS), and billing details. The roi_proof field quantifies how many tokens were saved and the cost savings in USD.","failureModes":["URL unreachable or returns non-200 status — distillation fails with an error status","Invalid or missing URL when html is not provided — schema validation error","Token budget too low (below 20) — rejected by schema validation","Malformed HTML that cannot be parsed — may return empty or degraded distillation","Rate limiting or payment failure via x402 — 402 response requiring USDC payment","Timeout fetching large or slow-loading pages — partial or failed distillation"],"whenToPreferThis":"Choose this endpoint when you need to feed live web content or raw HTML into an LLM context window and want to minimize token usage and cost. It is especially valuable when you have a specific query focus (use budget+BM25 mode) or need structured extraction from messy HTML. Prefer it over raw web scraping when you want token-efficient, LLM-ready output with built-in cost savings telemetry.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:37:32.742Z","isFirstParty":false,"canonicalSlug":"sec-intel-agentdiet-dev-url-html-markdown-distiller-with-bm25-budget-b3fa721b"}