{"uid":"cap_Y-0l7UPHlMlEqPr0Swkis","slug":"agentdiet-dev-agentdiet-web-distillation-api-bm25-budget-control-a315c588","name":"AgentDiet Web Distillation API (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/api/diet)","url":"https://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_XkMZXYxa5q-TxxW20sFzG","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, skeleton outline, or BM25-focused token-budget excerpts to reduce LLM token costs","exampleAgentPrompt":"Distill the article at https://example.com/long-article into focused markdown about 'transformer architecture' using budget mode with a max of 500 tokens, so I can pass just the relevant parts to my LLM.","exampleUseCases":[{"title":"Token-budget research digest","prompt":"Fetch https://arxiv.org/abs/2310.06825 and distill it down to at most 300 tokens focused on the query 'RLHF reward modeling' using budget mode — I need just the key points without blowing my context window."},{"title":"Clean markdown from noisy webpage","prompt":"Grab the content from https://stripe.com/docs/payments/payment-intents and convert it to clean markdown — strip all the nav, ads, and boilerplate so I can read the actual docs."},{"title":"Structured data extraction from HTML","prompt":"I have this raw HTML from a product page — can you distill it in structured mode to pull out the tables, metadata, and key specs as JSON so I can process it programmatically?"}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown text, 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 cache status (HIT/MISS) and billing details.","failureModes":["URL is unreachable or returns non-200 HTTP status — endpoint may return an error status","Raw HTML is malformed or empty — distillation may produce empty or partial output","max_tokens is set too low (below 20) — validation error returned","BM25 query is missing when mode=budget — may fall back to default behavior or return an error","Rate limiting or payment failure via x402 — 402 Payment Required response","URL is behind authentication or a paywall — content fetch fails"],"whenToPreferThis":"Choose this endpoint when you need to compress webpage content before feeding it to an LLM to reduce token costs, especially when you have a strict token budget or want to focus content on a specific query via BM25. It is ideal for agentic pipelines that browse the web and need to pass clean, relevant text to downstream LLM calls without wasting context. Prefer it over generic scrapers when compression ratio and cost savings metrics matter, or when you need structured JSON output from HTML rather than raw text.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-28T06:44:16.689Z","isFirstParty":false,"canonicalSlug":"agentdiet-dev-agentdiet-web-distillation-api-bm25-budget-control-a315c588"}