{"uid":"cap_N9A2QoSU3XvKJzv6U-EMQ","slug":"agentdiet-dev-agentdiet-html-to-markdown-distiller-with-bm25-budget-e79a3a75","name":"AgentDiet 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://agentdiet.dev/v1/html-to-markdown)","url":"https://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_gvOPlWtzNklvPug8JkGqW","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"agentdiet.dev","brandSlug":"agentdiet-dev-mpp","brandBaseUrl":"https://agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Converts a URL or raw HTML payload into compact Markdown, structured data, or a token-budget excerpt using BM25 relevance scoring to minimize LLM token consumption","exampleAgentPrompt":"Fetch https://stripe.com/docs/api and distill it into clean Markdown using budget mode, focusing on the query 'payment intents' with a max of 2000 tokens, so I can feed just the relevant parts to my LLM.","exampleUseCases":[{"title":"Token-efficient webpage ingestion for AI pipeline","prompt":"Grab https://openai.com/research/gpt-4 and distill it into compact Markdown — I want the full page but compressed as much as possible to save tokens before I send it to my LLM."},{"title":"BM25 budget excerpt for targeted research","prompt":"Pull the content from https://arxiv.org/abs/2305.10601 and give me only the parts relevant to 'chain-of-thought prompting', keeping the output under 1500 tokens using budget mode."},{"title":"Structured data extraction from raw HTML","prompt":"I have a raw HTML blob from a product listing page — can you distill it into structured JSON tables and metadata so I can easily parse the prices, product names, and descriptions?"}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown, structured JSON, skeleton outline, or BM25-focused excerpt), an 'roi_proof' object showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved in USD, plus optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 status — endpoint returns error status","HTML payload is empty or malformed — distillation may return empty or partial content","max_tokens set below minimum of 20 — validation error returned","BM25 query provided but mode is not 'budget' — query may be ignored","URL behind authentication or paywall — content fetch fails or returns login page","Rate limiting or payment failure via x402 — request rejected with 402 Payment Required"],"whenToPreferThis":"Choose this endpoint when you need to feed web page content to an LLM and want to minimize token usage and cost. It is especially valuable when the target page is long or noisy and you need only the portions relevant to a specific query (use budget+BM25 mode). Prefer it over generic scrapers when compression ratio and token ROI matter, or when you need structured output (tables, metadata) rather than raw HTML. It also supports passing raw HTML directly, making it useful in pipelines where content is already fetched.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:34:58.832Z","isFirstParty":false,"canonicalSlug":"agentdiet-dev-agentdiet-html-to-markdown-distiller-with-bm25-budget-e79a3a75"}