{"uid":"cap_Hsx-3yrCJ21InuR0OdJVa","slug":"onchain-risk-agentdiet-dev-web-content-distillation-with-bm25-budget-a9fab5aa","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://onchain-risk.agentdiet.dev/v1/context-diet)","url":"https://onchain-risk.agentdiet.dev/v1/context-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_cVvgTUVVnyEZ5Q42lpjzh","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"onchain-risk.agentdiet.dev","brandSlug":"onchain-risk-agentdiet-dev-mpp","brandBaseUrl":"https://onchain-risk.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into compact, agent-ready content with optional BM25-ranked token-budget control for query-focused extraction.","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments into markdown using budget mode, focused on 'payment intents', and keep it under 500 tokens.","exampleUseCases":[{"title":"Token-efficient research on competitor pricing","prompt":"Fetch https://competitor.com/pricing and distill it into markdown, keeping the output under 300 tokens and focused on the query 'enterprise plan pricing'."},{"title":"Extracting SEC filing highlights for an agent","prompt":"Take this raw HTML from an SEC 10-K filing and distill it into structured JSON tables — pull out the financial tables and metadata so I can analyze them."},{"title":"Skeleton outline of a long documentation page","prompt":"Give me a skeleton outline of https://docs.openai.com/api-reference so I can quickly scan the structure without reading the whole thing."}],"resultDescription":"Returns a 'data' object containing the distilled content in the requested format (markdown, structured JSON, skeleton, or BM25 budget excerpt), along with an 'roi_proof' object showing raw vs distilled token counts, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and an ROI multiplier. Also includes cache status (HIT/MISS) and billing details.","failureModes":["URL is unreachable or returns non-200 — fetch failure with error status","HTML payload is empty or malformed — distillation returns minimal or empty data","max_tokens set too low for meaningful content — may return truncated or nearly empty excerpt","BM25 query provided without mode=budget — query may be ignored","Payment not included or insufficient — HTTP 402 response blocking execution","Rate limiting or upstream timeout on slow target URLs"],"whenToPreferThis":"Choose this endpoint when you need to reduce token consumption from web content before passing it to an LLM, especially when you have a strict context window budget or want query-focused excerpts via BM25 ranking. It is superior to raw web scraping for agent workflows because it returns pre-compressed, LLM-ready content with quantified token savings. Prefer over generic scrapers when you need structured output modes (markdown, JSON tables, skeleton) or when working with large documentation pages like Stripe or OpenAPI specs. The BM25 budget mode is uniquely suited for RAG pipelines where only query-relevant passages are needed.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:32:32.317Z","isFirstParty":false,"canonicalSlug":"onchain-risk-agentdiet-dev-web-content-distillation-with-bm25-budget-a9fab5aa"}