{"uid":"cap_B5E8WIJt8JAhXxPZllQRe","slug":"alpha-stream-agentdiet-dev-web-content-distillation-with-bm25-budget-a35830f9","name":"Web Content Distillation 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/paywall-clean-extract)","url":"https://alpha-stream.agentdiet.dev/v1/paywall-clean-extract?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_2sry2-DAKSfIQyoNdCZ13","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 a URL or accepts raw HTML and distills it into compact, agent-ready content using BM25-ranked token budgets for efficient LLM consumption","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments/checkout into compact markdown using budget mode, focused on 'payment integration steps', and keep it under 500 tokens.","exampleUseCases":[{"title":"Token-efficient documentation ingestion","prompt":"Pull the content from https://docs.openai.com/api-reference and distill it into budget mode with my query 'function calling examples' capped at 300 tokens so I can fit it in my prompt."},{"title":"Research article extraction for agent pipeline","prompt":"Fetch this news article at https://www.nytimes.com/2025/01/15/tech/ai-agents.html and distill it into clean markdown so my agent can read it without blowing the context window."},{"title":"Structured data extraction from HTML","prompt":"I have a raw HTML blob from a product listing page — distill it in structured mode so I get the tables, metadata, and key fields as JSON without all the noise."}],"resultDescription":"Returns a 'data' object containing the distilled content in the requested format (Markdown, structured JSON, skeleton outline, or BM25 budget excerpt), along with an roi_proof object showing raw vs. distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved in USD. Also includes optional cache hit/miss status and billing info.","failureModes":["URL is unreachable or returns non-200 status — distillation fails with fetch error","HTML payload is empty or malformed — returns error or empty data","max_tokens set too low to contain meaningful content — truncated or error response","BM25 query not provided when mode=budget — may default to full distillation","Paywall or bot-blocking on target URL — content may be incomplete","Invalid mode enum value — request rejected with validation error"],"whenToPreferThis":"Choose this endpoint when you need to read a webpage but want to minimize token usage before passing content to an LLM. It is especially valuable when using BM25 budget mode to extract only query-relevant passages from long pages, making it ideal for RAG pipelines, agent context windows, and cost-sensitive LLM workflows. Prefer it over raw scraping when clean markdown or structured output is needed, or when you want automatic ROI tracking of how many tokens were saved.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:31:19.359Z","isFirstParty":false,"canonicalSlug":"alpha-stream-agentdiet-dev-web-content-distillation-with-bm25-budget-a35830f9"}