{"uid":"cap_rInQcGhnBcWhAiBruTuQx","slug":"domain-osint-agentdiet-dev-web-content-distillation-with-bm25-budget-67855e78","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://domain-osint.agentdiet.dev/v1/context-diet)","url":"https://domain-osint.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_94ytSzJgjWisNGGuRqXnJ","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"domain-osint.agentdiet.dev","brandSlug":"domain-osint-agentdiet-dev-mpp","brandBaseUrl":"https://domain-osint.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into compressed Markdown, structured JSON, skeleton outline, or a BM25-ranked token-budget excerpt, returning ROI metrics on tokens saved.","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/payments/accept-a-payment and distill it into clean Markdown using budget mode, focused on the query 'payment intents', with a max of 500 tokens?","exampleUseCases":[{"title":"LLM cost-efficient doc lookup","prompt":"Grab the content from https://docs.openai.com/api-reference and distill it in budget mode focused on 'rate limits', keeping it under 300 tokens so I don't blow my context window."},{"title":"Structured data extraction from landing page","prompt":"Take this raw HTML I have from a competitor's pricing page and distill it into structured JSON tables so I can see their pricing tiers clearly."},{"title":"Skeleton outline of long article","prompt":"Distill https://en.wikipedia.org/wiki/Large_language_model into a skeleton outline mode so I get just the section headers and key structure without all the body text."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object with raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes cache status (HIT/MISS) and billing metadata.","failureModes":["Invalid or unreachable URL returns fetch error","HTML too large or malformed may cause partial distillation","max_tokens too low (below 20) returns validation error","BM25 query missing when mode=budget may return unfiltered content","Rate limiting or payment failure (x402) blocks the request","Cached responses may be stale if content changes frequently"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to consume web page content within a strict token budget, minimize LLM inference costs, or extract clean structured content from noisy HTML. It is especially valuable when feeding live documentation, news articles, or competitor pages into an LLM context window. The BM25 budget mode makes it uniquely suitable for query-focused retrieval where only the most relevant passage of a page is needed.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:35:14.217Z","isFirstParty":false,"canonicalSlug":"domain-osint-agentdiet-dev-web-content-distillation-with-bm25-budget-67855e78"}