{"uid":"cap_2ru8khT9PWXgzgAkjqXfw","slug":"workflows-agentdiet-dev-webpage-distiller-with-bm25-budget-control-4b762a42","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://workflows.agentdiet.dev/v1/webpage-distiller)","url":"https://workflows.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_U5tGXw7PKKbi4wvtNvcUH","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 and distills a URL or raw HTML into compact, token-efficient markdown, structured JSON, outline skeleton, or BM25-scored excerpt within a strict token budget","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it into compact markdown using budget mode, focused on the query 'payment intents', with a max of 500 tokens.","exampleUseCases":[{"title":"Research page distillation for LLM context","prompt":"Pull https://openai.com/research/gpt-4 and distill it into markdown so I can drop it into my prompt without blowing the context window."},{"title":"BM25 focused excerpt for RAG pipeline","prompt":"Distill https://docs.aws.amazon.com/s3/latest/userguide/Welcome.html in budget mode with the query 'presigned URLs' and cap the output at 300 tokens — I only want the most relevant section."},{"title":"Structured product data from raw HTML","prompt":"I have raw HTML from a SaaS pricing page — distill it into structured JSON so I can extract the pricing tiers and feature lists without parsing it myself."}],"resultDescription":"Returns a distilled representation of the webpage in the requested mode (markdown, structured JSON tables/metadata, skeleton outline, or BM25-ranked budget excerpt), along with an ROI proof object showing raw token count, distilled token count, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and a ROI multiplier. Also includes cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","HTML payload too large may exceed processing limits","mode=budget without a query or max_tokens may return unfiltered content","Network timeout if the target URL is slow to respond","Malformed HTML may produce incomplete or inaccurate distillation","Token budget too small (below 20) returns a validation error"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web content but must stay within a token budget or minimize LLM inference cost. It is especially valuable for RAG pipelines, research agents, and agentic workflows that routinely fetch multiple pages and need BM25-ranked excerpts scoped to a specific query. Prefer it over raw web scraping when you need token-efficient, agent-ready output rather than raw HTML, and when you want built-in ROI accounting showing exactly how many tokens and dollars were saved.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:31:45.001Z","isFirstParty":false,"canonicalSlug":"workflows-agentdiet-dev-webpage-distiller-with-bm25-budget-control-4b762a42"}