{"uid":"cap_zrDB2dXcQ3NmYJ4iR6kFQ","slug":"agentdiet-dev-agentdiet-web-distiller-with-bm25-budget-control-aad6a6bc","name":"AgentDiet Web 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://agentdiet.dev/)","url":"https://agentdiet.dev/?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_DVf_YJ-hz7aRAV20dZ1sY","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 outlines, or BM25-ranked token-budget excerpts for LLM-efficient consumption","exampleAgentPrompt":"Fetch the page at https://stripe.com/docs/payments and distill it into markdown, keeping it under 2000 tokens — only the parts relevant to 'payment intents'.","exampleUseCases":[{"title":"Token-efficient research from live URLs","prompt":"Go to https://openai.com/research/gpt-4 and give me a distilled markdown summary, keeping it under 1500 tokens so it fits in my context window."},{"title":"Focused BM25 excerpt for a specific question","prompt":"Fetch https://docs.uniswap.org/contracts/v3/overview and return only the sections most relevant to 'fee tiers and liquidity pools' in budget mode with a max of 800 tokens."},{"title":"Structured data extraction from a webpage","prompt":"Pull the page at https://news.ycombinator.com and distill it into structured JSON tables showing the top stories, scores, and comment counts."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown, structured tables, skeleton outline, or BM25 excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd, along with cache status and billing details.","failureModes":["URL is unreachable or returns a non-200 HTTP status — endpoint returns an error status","HTML payload is empty or malformed — distillation may return minimal or empty content","max_tokens ceiling is set too low (below 20) — rejected by schema validation","BM25 query is missing when mode=budget — may return unfiltered or fallback content","Target site blocks automated fetching (bot protection) — fetch fails or returns incomplete HTML","Token budget exceeded by raw content before distillation — output may be truncated"],"whenToPreferThis":"Choose this endpoint when you need to feed web content to an LLM but want to minimize token usage and cost. It is especially valuable when you have a specific query and want BM25-ranked excerpts (mode=budget) rather than full-page dumps, or when you want structured JSON tables or skeleton outlines instead of raw HTML. Prefer it over generic scrapers when token ROI and compression ratio matter, or when you need a built-in proof of savings for billing optimization.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:31:48.510Z","isFirstParty":false,"canonicalSlug":"agentdiet-dev-agentdiet-web-distiller-with-bm25-budget-control-b4a0e39f"}