{"uid":"cap_NhP58N9royq9BW_Kxsi28","slug":"llms-generator-agentdiet-dev-webpage-distiller-with-bm25-budget-control-eace8650","name":"Webpage 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/webpage-distiller)","url":"https://llms-generator.agentdiet.dev/v1/webpage-distiller?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_zjBAAEKraiLnpx8KFIJTm","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 and distills a URL or raw HTML into clean Markdown, structured JSON, a skeleton outline, or a BM25-focused token-budgeted excerpt","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments into clean markdown and keep it under 2000 tokens, focusing on the topic 'payment intent creation' using BM25 budget mode?","exampleUseCases":[{"title":"LLM context window optimization","prompt":"Fetch https://docs.openai.com/api-reference and distill it in budget mode focused on 'function calling', with a max token ceiling of 1500 tokens — I want to feed only the relevant bits to my LLM."},{"title":"Structured product data extraction","prompt":"Take the HTML from this e-commerce page and distill it in structured mode so I get the product names, prices, and metadata as clean JSON tables rather than raw HTML."},{"title":"Research page skeleton outline","prompt":"Distill https://arxiv.org/abs/2307.09288 in skeleton mode so I get a quick outline of the paper's sections and headings without reading the full content."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes cache hit/miss status and billing details.","failureModes":["URL unreachable or returns non-200 status — distillation fails with fetch error","HTML payload too large or malformed — may produce incomplete distillation","mode=budget with no query provided — BM25 scoring has no focus signal, falls back or errors","max_tokens too small (below 20) — rejected by schema validation","Rate limit or payment failure via x402 — returns 402 Payment Required","Paywalled or JavaScript-rendered pages may return minimal or empty content"],"whenToPreferThis":"Choose this endpoint when you need to feed webpage content to an LLM and want to minimize token usage through compression and BM25-focused excerpting. It is especially valuable when working with long documentation pages, e-commerce catalogs, or research articles where only a subset of content is relevant to a specific query. Prefer it over generic web scrapers when token budget control and ROI reporting matter, or when you need structured JSON extraction rather than raw HTML.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:35:10.815Z","isFirstParty":false,"canonicalSlug":"llms-generator-agentdiet-dev-webpage-distiller-with-bm25-budget-control-eace8650"}