{"uid":"cap_Jb2ZVWL8bOcWICKfr1JGL","slug":"llms-generator-agentdiet-dev-web-url-html-distiller-with-bm25-budget-9f3c1f9f","name":"Web URL & HTML 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://llms-generator.agentdiet.dev/v1/docs-to-markdown)","url":"https://llms-generator.agentdiet.dev/v1/docs-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_EA3vSP0NIjb2IlrAHVnTY","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"llms-generator.agentdiet.dev","brandSlug":"llms-generator-agentdiet-dev-mpp","brandBaseUrl":"https://llms-generator.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into clean Markdown, structured JSON, a skeleton outline, or a BM25-ranked token-budget excerpt","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments into clean markdown and keep it under 2000 tokens, focusing on the query 'payment intents setup' using budget mode.","exampleUseCases":[{"title":"Documentation summarization for agent context","prompt":"Grab the content from https://docs.openai.com/api-reference and distill it into a skeleton outline so I can see the structure without blowing my token budget."},{"title":"Focused BM25 extraction from a long page","prompt":"Fetch https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) and return only the sections most relevant to 'attention mechanism' using budget mode, capped at 1500 tokens."},{"title":"Convert raw HTML to structured markdown","prompt":"I have this raw HTML from a product page — distill it into clean structured markdown with any tables preserved as JSON so I can feed it into my pipeline."}],"resultDescription":"Returns a JSON object containing: a 'data' field with the distilled output (Markdown string, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode); an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd; optional 'cache' metadata (HIT/MISS, cache_key, latency_ms); optional 'billing' info; and a 'status' field ('ok' on success).","failureModes":["URL unreachable or returns non-200 — endpoint may return error status","Invalid or malformed URL string — validation error on required 'url' field","Token budget too low (max_tokens < 20) — rejected by schema validation","Mode 'budget' used without providing a 'query' — BM25 ranking cannot proceed","Raw HTML too large — may exceed processing limits","Payment failure via x402 — 402 response if USDC payment not attached","Idempotency-Key conflict — repeated key with different payload may return cached prior result"],"whenToPreferThis":"Choose this endpoint when you need to extract clean, token-efficient content from a live URL or raw HTML for downstream LLM processing — especially when token cost matters. The BM25 budget mode is uniquely suited for retrieving only the most query-relevant sections of a long page within a strict token ceiling, which no generic scraper provides. Prefer it over generic scrapers when you need ROI proof (compression ratio, tokens saved) or when you want structured output (tables, skeleton) rather than raw HTML dumps.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:35:09.139Z","isFirstParty":false,"canonicalSlug":"llms-generator-agentdiet-dev-web-url-html-distiller-with-bm25-budget-9c254370"}