{"uid":"cap_dMI0qtWcFCGKKQz9tJVXX","slug":"sec-intel-agentdiet-dev-webpage-distiller-with-bm25-budget-control-6dac6e95","name":"Webpage 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://sec-intel.agentdiet.dev/v1/webpage-distiller)","url":"https://sec-intel.agentdiet.dev/v1/webpage-distiller?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_0uMjoxwC-Nci8opdOaVK0","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 JSON, skeleton outline, or BM25-ranked token-budget excerpt","exampleAgentPrompt":"Distill the webpage at https://stripe.com/docs/payments into compressed markdown, using budget mode focused on the query 'payment intents API' and keep it under 500 tokens.","exampleUseCases":[{"title":"Token-budget research for LLM pipeline","prompt":"Fetch the article at https://www.wired.com/story/openai-gpt5/ and distill it into budget mode focused on the query 'GPT-5 capabilities', keeping the output under 300 tokens so I can pass it to my model cheaply."},{"title":"Structured data extraction from product page","prompt":"Pull the page at https://aws.amazon.com/ec2/pricing/ and distill it in structured mode so I get the pricing tables and metadata as clean JSON I can parse programmatically."},{"title":"Skeleton outline of long documentation","prompt":"Take https://docs.stripe.com/api and give me a skeleton outline distillation so I can quickly see the high-level structure of the Stripe API docs without reading the whole thing."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown text, structured JSON tables/metadata, outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns fetch error","HTML too large or malformed may produce incomplete distillation","max_tokens below minimum (20) returns validation error","mode=budget without a query may produce unfocused excerpt","Paywalled or JS-rendered pages may return incomplete content","Payment/402 failure if USDC balance insufficient","Rate limiting if too many requests in short period"],"whenToPreferThis":"Choose this endpoint when you need to feed webpage content to an LLM but want to minimize token usage and cost — especially with strict context window limits. It is preferable to raw fetch + manual parsing when you need built-in BM25 relevance filtering around a specific query, or when you want structured JSON tables/metadata extracted automatically. Ideal for agentic pipelines where web content must be compressed before downstream LLM calls, and when you need quantified proof of token savings (ROI metrics).","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:30:21.410Z","isFirstParty":false,"canonicalSlug":"sec-intel-agentdiet-dev-webpage-distiller-with-bm25-budget-control-6dac6e95"}