{"uid":"cap_qMillZEBKnzM5MpcR8TJu","slug":"agentdiet-dev-agentdiet-markdown-distill-bm25-budget-control-6a04eaf2","name":"AgentDiet Markdown Distill (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/v1/markdown-distill)","url":"https://agentdiet.dev/v1/markdown-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__omOmIsJ42EwmzyRe0vwF","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","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, a skeleton outline, or a BM25-ranked token-budget excerpt — returning ROI proof of tokens saved.","exampleAgentPrompt":"Distill the Stripe documentation page at https://stripe.com/docs/api/charges into a BM25 budget excerpt focused on 'refund a charge', and keep it under 500 tokens so I can paste it into my prompt.","exampleUseCases":[{"title":"Token-efficient doc lookup for agent","prompt":"Fetch the page at https://docs.openai.com/api-reference and distill it into a budget excerpt about 'streaming completions' — cap it at 300 tokens so it fits in my context window."},{"title":"Structured table extraction from HTML","prompt":"I have raw HTML from a pricing comparison page — can you distill it into structured JSON tables so I can see all the plan names and prices clearly?"},{"title":"Documentation skeleton for navigation","prompt":"Can you fetch https://docs.python.org/3/library/asyncio.html and give me a skeleton outline of the page so I know what sections exist before I dive in?"}],"resultDescription":"Returns a JSON object with a `data` field 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_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 — fetch failure error","HTML payload is empty or malformed — distillation returns minimal or empty content","mode=budget without a query or max_tokens — may fall back to default markdown mode","Token budget too low (below 20) — rejected by schema validation","Rate limiting or payment failure via x402 — 402 Payment Required response","Idempotency-Key collision across different payloads — may return cached result unexpectedly"],"whenToPreferThis":"Choose this endpoint when your agent needs to consume web page content within a strict token budget, especially when full-page HTML would overflow an LLM context window. The BM25 budget mode is uniquely suited when you have a specific query and want only the most relevant passage from a long page. Prefer it over generic web scrapers when you need compression ratio proofs and LLM cost savings metadata alongside the content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:35:34.063Z","isFirstParty":false,"canonicalSlug":"agentdiet-dev-agentdiet-markdown-distill-bm25-budget-control-6a04eaf2"}