{"uid":"cap_XlLClxQYLo9haAKldlv5W","slug":"sec-intel-agentdiet-dev-web-distillation-with-bm25-budget-control-5abbb3ef","name":"Web 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://sec-intel.agentdiet.dev/api/diet)","url":"https://sec-intel.agentdiet.dev/api/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_9kWAJxZAfgFZUGBRyXHPG","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"sec-intel.agentdiet.dev","brandSlug":"sec-intel-agentdiet-dev-mpp","brandBaseUrl":"https://sec-intel.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into compressed Markdown, structured data, skeleton outline, or a BM25-focused token-budget excerpt","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments/accept-a-payment and distill it into markdown using budget mode with a max of 500 tokens, focusing on the query 'payment intent setup'.","exampleUseCases":[{"title":"Token-efficient research on live docs","prompt":"Pull https://docs.openai.com/api-reference/chat and distill it in budget mode with a max of 800 tokens, focusing on the query 'streaming responses' — I want only the most relevant content without burning through my context window."},{"title":"Structured data extraction from product page","prompt":"Fetch https://aws.amazon.com/ec2/pricing/ and distill it in structured mode so I get tables and metadata about EC2 instance pricing in JSON format."},{"title":"Outline skeleton of a long article","prompt":"Take this raw HTML from a news article and give me a skeleton outline of its sections and headings so I can decide which parts to read in full."}],"resultDescription":"Returns a data object with the distilled content (Markdown, structured JSON, skeleton, or BM25 excerpt), an roi_proof block showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved, plus optional billing and cache status fields.","failureModes":["URL is unreachable or returns non-200 — fetch failure error","HTML payload is empty or malformed — parse error","max_tokens set below 20 — validation error","mode=budget used without a query — missing query parameter error","Payment not provided or insufficient — HTTP 402 response","Rate limit exceeded — 429 error"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read web pages or HTML documents without consuming large numbers of tokens, especially when a strict context budget must be respected or only query-relevant content is needed. Prefer over raw fetch when token cost reduction, structured extraction, or BM25-focused relevance filtering matters. Particularly valuable for processing long documentation pages, SEC filings, or product catalogs where only a portion is relevant.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:36:06.640Z","isFirstParty":false,"canonicalSlug":"sec-intel-agentdiet-dev-web-distillation-with-bm25-budget-control-bba76e87"}