{"uid":"cap_DfgW7vy1TxpC3HFT_VsOB","slug":"workflows-agentdiet-dev-web-url-html-distiller-with-bm25-budget-control-e2efa402","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://workflows.agentdiet.dev/v1/distill)","url":"https://workflows.agentdiet.dev/v1/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_3SO6sg8D_xpECNe6MiBxc","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"workflows.agentdiet.dev","brandSlug":"workflows-agentdiet-dev-mpp","brandBaseUrl":"https://workflows.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or raw HTML and distills it into compact, agent-ready tokens using markdown, structured, skeleton, or BM25-focused budget modes.","exampleAgentPrompt":"Distill the page at https://docs.stripe.com/payments into compact markdown, using budget mode focused on the query 'payment intents' with a max of 500 tokens, so I can fit it into my context window.","exampleUseCases":[{"title":"Token-efficient doc ingestion for agents","prompt":"Fetch https://docs.openai.com/api-reference and distill it into budget mode focused on the query 'streaming responses', capped at 800 tokens, so I can include it in my prompt without blowing the context limit."},{"title":"Structured product data from e-commerce page","prompt":"Take this raw HTML from a Shopify store and distill it into structured mode so I can extract the product names, prices, and variants as clean JSON."},{"title":"Skeleton outline of a long article","prompt":"Distill https://en.wikipedia.org/wiki/Large_language_model into skeleton mode so I get just the section headings and a brief outline without all the full text."}],"resultDescription":"Returns a JSON object containing the distilled content (markdown, structured tables/metadata, skeleton outline, or BM25-filtered excerpt), an roi_proof block showing raw vs distilled token counts, compression ratio, and estimated LLM cost saved, plus optional cache status and billing details.","failureModes":["URL unreachable or returns non-200 — distillation fails with a fetch error","HTML payload is empty or malformed — may return empty or poor-quality distillation","mode=budget used without a query parameter — BM25 filtering cannot focus without a query","max_tokens set below page minimum useful size — truncation may lose critical content","Payment not processed — HTTP 402 returned if x402 credentials are missing or invalid","Rate limits or SLA timeouts for very large pages — latency spike or timeout error"],"whenToPreferThis":"Choose this endpoint when you need to reduce a webpage or raw HTML to a minimal token footprint before passing content to an LLM, especially when working under tight context budgets. The BM25 budget mode is uniquely useful when you only want the page sections most relevant to a specific query. Prefer this over generic scrapers when you need token savings quantified (roi_proof) or when you want multiple distillation modes (markdown, structured, skeleton, budget) from a single API call.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:36:43.007Z","isFirstParty":false,"canonicalSlug":"workflows-agentdiet-dev-web-url-html-distiller-with-bm25-budget-control-57a891e7"}