{"uid":"cap_-YTcwBRHgjIX0jfSwuS80","slug":"agentdiet-dev-agentdiet-web-distill-bm25-budget-controlled-html-url-91bbff36","name":"AgentDiet Web Distill – BM25 Budget-Controlled HTML/URL Distillation","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://agentdiet.dev/v1/distill)","url":"https://agentdiet.dev/v1/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_cDdG9hSnzn1Dp5FAoE3Rl","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 content at https://stripe.com/docs/payments into compressed markdown mode and then also give me a BM25-focused budget excerpt about 'payment intents' with a max of 300 tokens — I want to see how many tokens you saved.","exampleUseCases":[{"title":"Token-budget research before LLM call","prompt":"Fetch https://openai.com/research/gpt-4 and distill it into a BM25 budget excerpt focused on 'context window size', capped at 400 tokens — I need to stay within my prompt budget."},{"title":"Structured data extraction from docs page","prompt":"Pull the Stripe pricing page at https://stripe.com/pricing and distill it in structured mode so I get the pricing tiers and fees as JSON tables, not raw HTML."},{"title":"Skeleton outline for long article","prompt":"Take this raw HTML I'll paste — it's a long TechCrunch article — and give me a skeleton outline of all the headings and subheadings so I can decide which sections are worth reading in full."}],"resultDescription":"Returns a JSON object with: `data` containing the distilled content (Markdown string, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode); `roi_proof` with raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd; optional `cache` hit/miss status and latency; optional `billing` with fee charged in USD; and `status` ('ok') on success.","failureModes":["URL unreachable or returns non-200 HTTP — endpoint may return an error status","HTML too large or malformed — distillation may be incomplete or fail","BM25 query missing when mode=budget — defaults may apply or error returned","max_tokens below minimum of 20 — validation error","Payment/402 failure — billing not resolved, request rejected","Invalid mode enum value — schema validation error"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web page content but must stay within a token budget or minimize LLM costs — especially for long documentation pages, research articles, or HTML dumps. The BM25 budget mode is uniquely suited for query-focused extraction when only a portion of a page is relevant. Prefer this over generic scrapers when token ROI proof and compression metrics matter to the downstream workflow, or when you need structured JSON tables rather than raw HTML.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:36:47.076Z","isFirstParty":false,"canonicalSlug":"agentdiet-dev-agentdiet-web-distill-bm25-budget-controlled-html-url-91bbff36"}