{"uid":"cap_0t3B6OP12fHOijzDBi8rx","slug":"company-enrich-agentdiet-dev-distill-url-or-html-with-bm25-budget-0186a3be","name":"Distill URL or HTML 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://company-enrich.agentdiet.dev/api/diet)","url":"https://company-enrich.agentdiet.dev/api/diet?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_q3xHyUxZmzdN70vYPU-wU","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"company-enrich.agentdiet.dev","brandSlug":"company-enrich-agentdiet-dev-mpp","brandBaseUrl":"https://company-enrich.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and compresses a webpage URL or raw HTML into clean Markdown, structured JSON, a skeleton outline, or a BM25-ranked token-budgeted excerpt.","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments into clean markdown using budget mode, focused on 'payment intent creation', and keep it under 500 tokens?","exampleUseCases":[{"title":"Token-efficient docs for LLM context","prompt":"Pull the content from https://docs.anthropic.com/claude/reference and distill it into budget mode focused on 'tool use', keeping it under 300 tokens so I can fit it in my prompt."},{"title":"Extract structured company data from webpage","prompt":"Distill https://openai.com/about into structured mode so I can get the tables and key metadata about the company without all the HTML noise."},{"title":"Clean markdown from raw HTML email","prompt":"I have a raw HTML newsletter body — can you distill it into clean markdown so I can read it without all the tags and boilerplate?"}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown string, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Also includes cache status (HIT/MISS) and billing details.","failureModes":["URL is unreachable or returns non-200 — fetch error returned","HTML payload is empty or malformed — distillation returns empty or error","max_tokens ceiling too low (below 20) — schema validation error","BM25 query provided without mode=budget — query may be ignored","Rate limit or payment failure via x402 — 402 response with payment details","URL is a non-HTML resource (PDF, binary) — may produce garbled output"],"whenToPreferThis":"Choose this endpoint when you need to reduce the token footprint of a webpage or HTML document before sending it to an LLM, especially when you have a strict context budget or a specific topic focus. The BM25 budget mode is uniquely suited for extracting only the most query-relevant passages from long pages. Prefer this over generic scrapers when you need quantified compression ROI (tokens saved, cost saved) and multiple distillation modes (markdown, structured, skeleton, budget) in a single API.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:37:47.037Z","isFirstParty":false,"canonicalSlug":"company-enrich-agentdiet-dev-distill-url-or-html-with-bm25-budget-0186a3be"}