{"uid":"cap_ISOkILej8H3GHh87otVm7","slug":"alpha-stream-agentdiet-dev-agentdiet-web-distiller-with-bm25-budget-d95bc467","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/clean-html)","url":"https://alpha-stream.agentdiet.dev/v1/clean-html?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_F3K2XyjfE_X2X75wvU3l-","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 compact, agent-ready Markdown, structured JSON, skeleton outline, or BM25-focused budget excerpt with token savings proof","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into clean markdown with a 500-token budget focused on the query 'payment intents API' so I can fit it into my context window.","exampleUseCases":[{"title":"Compress docs page into context window","prompt":"Take this URL https://docs.openai.com/api-reference and distill it into markdown using a 400-token budget focused on the query 'function calling' — I need it small enough to paste into my prompt."},{"title":"Extract structured tables from financial page","prompt":"Fetch https://finance.yahoo.com/quote/AAPL and distill it in structured mode so I get the key financial tables and metadata as JSON."},{"title":"Summarize raw HTML with strict token cap","prompt":"I have this raw HTML blob from a competitor pricing page — distill it in budget mode with a 300-token ceiling and focus the BM25 query on 'enterprise pricing tiers'."}],"resultDescription":"Returns a distilled representation of the webpage or HTML in the requested mode (Markdown, structured JSON, skeleton, or BM25 budget excerpt), along with ROI proof metrics including raw token count, distilled token count, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and optionally cache hit/miss status and billing details.","failureModes":["URL unreachable or returns non-200 — fetch failure with error status","HTML too short or empty — minimal or empty distillation output","max_tokens below minimum of 20 — validation error","BM25 query missing when mode=budget — may default or return error","Rate limiting or payment failure via x402 — 402 Payment Required response","Invalid URL format — schema validation rejection"],"whenToPreferThis":"Choose this endpoint when you need to shrink web pages or HTML blobs into LLM-consumable tokens while maintaining semantic relevance — especially when operating under strict context window constraints. The BM25 budget mode is uniquely valuable when you want to focus distillation on a specific topic query rather than generic summarization. Prefer over generic scrapers when you need token savings proof and cost metrics alongside the content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:37:18.104Z","isFirstParty":false,"canonicalSlug":"alpha-stream-agentdiet-dev-agentdiet-web-distiller-with-bm25-budget-06f5e814"}