{"uid":"cap_tDJFiJFSn65HUnnLKuCfl","slug":"agentdiet-dev-agentdiet-web-distillation-with-bm25-budget-control-5028e280","name":"AgentDiet Web Distillation 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/a2a)","url":"https://agentdiet.dev/a2a?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":"0.001000","displayCostAsset":"USD","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"registry","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":"$0.001000/call","primary":{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.001000","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.001000","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_gNXVvitFpTmpqRCPJI4rL","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001000","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":"agentdiet.dev","brandSlug":"agentdiet-dev-mpp","brandBaseUrl":"https://agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into compressed Markdown, structured JSON, skeleton outline, or a BM25-ranked token-budgeted excerpt","exampleAgentPrompt":"Fetch the Stripe documentation page at https://stripe.com/docs/payments and distill it in budget mode focused on 'payment intents', keeping it under 500 tokens, so I can feed it to my LLM without blowing my context window.","exampleUseCases":[{"title":"LLM-ready webpage compression","prompt":"Grab the content from https://openai.com/pricing and distill it into markdown so I can include it in my prompt without wasting tokens."},{"title":"BM25 budget excerpt for RAG pipeline","prompt":"Distill https://docs.anthropic.com/claude/reference/messages in budget mode, focused on the query 'tool use streaming', with a max of 300 tokens — I only need the relevant parts for my retrieval pipeline."},{"title":"Structured data extraction from raw HTML","prompt":"I have a raw HTML blob from a financial news article — distill it into structured mode so I get clean JSON tables and metadata I can parse programmatically."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt), plus an 'roi_proof' object with raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes cache status (HIT/MISS) and billing details.","failureModes":["URL is unreachable or returns non-200 status — distillation fails with an error status","Raw HTML is malformed and cannot be parsed — returns empty or partial data","max_tokens is set too low to return meaningful content — truncated or empty excerpt","BM25 query finds no relevant sections — returns minimal or empty budget excerpt","Rate limiting or payment failure via x402 — request rejected before processing","URL is blocked by robots.txt or requires authentication — fetch fails"],"whenToPreferThis":"Choose this endpoint when you need to feed web content to an LLM but want to minimize token usage and cost. It's especially valuable when working with long documentation pages, news articles, or any raw HTML where only a subset is relevant to a specific query. The BM25 budget mode makes it uniquely suited for RAG pipelines where you need a focused, token-capped excerpt. Prefer this over generic scrapers when you need built-in compression metrics and LLM cost accounting.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:35:59.341Z","isFirstParty":false,"canonicalSlug":"agentdiet-dev-agentdiet-web-distillation-with-bm25-budget-control-e8a546c8"}