{"uid":"cap_eGEmnvAX0-se5gTL3PeVe","slug":"alpha-stream-agentdiet-dev-agentdiet-web-distiller-with-bm25-budget-06f5e814","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://alpha-stream.agentdiet.dev/v1/distill)","url":"https://alpha-stream.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_acHAM9L2pZcQPrR-cfHFc","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"alpha-stream.agentdiet.dev","brandSlug":"alpha-stream-agentdiet-dev-mpp","brandBaseUrl":"https://alpha-stream.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into Markdown, structured JSON, skeleton outline, or a BM25-ranked token-budgeted excerpt","exampleAgentPrompt":"Distill the content at https://docs.stripe.com/payments into clean markdown, and keep it under 2000 tokens using BM25 budget mode focused on 'payment intents'.","exampleUseCases":[{"title":"Token-budget research grounding","prompt":"I need you to fetch https://en.wikipedia.org/wiki/Transformer_(deep_learning_architecture) and give me a BM25-focused excerpt about 'attention mechanism' with a strict cap of 500 tokens so I don't blow my context window."},{"title":"Structured data extraction from docs","prompt":"Pull the content from https://stripe.com/docs/api and distill it into structured JSON tables and metadata — I want to see the organized data, not a wall of text."},{"title":"Readable markdown from noisy HTML","prompt":"I have some raw HTML from a news article with tons of ads and nav menus — can you distill it into clean markdown for me? Here's the HTML: <html><body>...</body></html>"}],"resultDescription":"Returns a JSON object containing: distilled content in the requested format (Markdown, structured JSON, skeleton, or BM25 excerpt) under 'data'; an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, ROI multiplier, and estimated LLM cost saved in USD; optional cache hit/miss status with latency; and billing details including fee charged.","failureModes":["URL unreachable or returns non-200: fetch failure with status error","Invalid or empty URL provided: validation error","mode=budget used without query parameter: missing BM25 focus query error","max_tokens set below minimum of 20: schema validation rejection","Raw HTML too large for processing: payload size exceeded","Paywalled or bot-blocked pages: content extraction failure","x402 payment not attached or insufficient: 402 Payment Required response"],"whenToPreferThis":"Choose this endpoint when you need to reduce token consumption from web pages before feeding content to an LLM — especially when you have a strict token budget and a specific focus query (mode=budget with BM25 ranking). Prefer it over generic scrapers when you want ROI-quantified compression with multiple output modes (markdown, structured, skeleton). Ideal for agentic workflows where context window costs matter and content relevance must be maximized per token.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:37:10.143Z","isFirstParty":false,"canonicalSlug":"alpha-stream-agentdiet-dev-agentdiet-web-distiller-with-bm25-budget-06f5e814"}