{"uid":"cap_97KxGI9KnvQ--g6bSS-dZ","slug":"sec-intel-agentdiet-dev-web-url-distiller-rag-chunker-8e52fa5d","name":"Web URL Distiller & RAG Chunker","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/rag-chunk)","url":"https://sec-intel.agentdiet.dev/v1/rag-chunk?utm_source=zero.xyz","method":"GET","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_f4unMN6eaE8UODiRSS7H-","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 a webpage or raw HTML and distills it into compact, agent-ready tokens using BM25 budget control and multiple extraction modes","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into compact markdown — use budget mode with a 500-token ceiling, focused on the query 'payment intents API'.","exampleUseCases":[{"title":"RAG pipeline doc ingestion","prompt":"Fetch and distill https://docs.openai.com/api-reference into structured JSON tables so I can load it into my RAG pipeline without blowing my token budget."},{"title":"Focused research excerpt on a topic","prompt":"Grab https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) and give me only the parts relevant to 'attention mechanism' — use budget mode with a 300-token max."},{"title":"Skeleton outline for agent navigation","prompt":"Get a skeleton outline of https://developer.mozilla.org/en-US/docs/Web/API so my agent can navigate the structure without reading the full page."}],"resultDescription":"Returns a 'data' object containing the distilled content in the requested format (Markdown, structured JSON, skeleton outline, or BM25-focused excerpt), plus an ROI proof object showing raw vs. distilled token counts, tokens saved, compression ratio, and estimated LLM cost saved. Also includes optional cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns fetch error","max_tokens below minimum of 20 returns validation error","mode=budget without a query may return unfiltered truncation","HTML payload too large may time out or be partially processed","Paywalled or bot-blocked pages may return incomplete content","Payment failure via x402 returns 402 with payment details"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM or RAG pipeline and want to minimize token usage. It is especially useful when you have a strict token budget (use budget mode with BM25 query) or need structured/skeleton extraction rather than raw HTML. Prefer it over generic scrapers when ROI tracking and token compression metrics matter to your pipeline.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:45.326Z","isFirstParty":false,"canonicalSlug":"sec-intel-agentdiet-dev-web-url-distiller-rag-chunker-8e52fa5d"}