{"uid":"cap_JUaufT4paHG6zFeqszElw","slug":"preflight-agentdiet-dev-agentdiet-rag-chunk-web-url-distillation-d7cf7509","name":"AgentDiet RAG Chunk - Web URL Distillation","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://preflight.agentdiet.dev/v1/rag-chunk)","url":"https://preflight.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_wiJDW3ryDtrt7ul7JuIak","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"preflight.agentdiet.dev","brandSlug":"preflight-agentdiet-dev-mpp","brandBaseUrl":"https://preflight.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a web URL or raw HTML into compact, token-efficient Markdown, structured JSON, skeleton outline, or BM25-focused excerpts for AI agent consumption","exampleAgentPrompt":"Distill the content at https://docs.stripe.com/payments/checkout into compact Markdown using budget mode, focusing on 'payment intents', and keep it under 500 tokens.","exampleUseCases":[{"title":"RAG pipeline web grounding","prompt":"Fetch and distill https://openai.com/blog/gpt-4o into clean Markdown so I can feed it into my RAG pipeline without blowing my token budget."},{"title":"Structured data extraction from docs","prompt":"Pull the pricing table from https://www.anthropic.com/pricing and return it as structured JSON so my agent can compare model costs."},{"title":"Focused excerpt for research query","prompt":"From https://en.wikipedia.org/wiki/Transformer_(machine_learning_model), extract only the sections most relevant to 'attention mechanism' using budget mode and cap it at 300 tokens."}],"resultDescription":"Returns a JSON object containing the distilled content (as Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt), an ROI proof block showing raw vs distilled token counts, tokens saved, compression ratio percentage, and estimated LLM cost saved, plus optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 HTTP status — endpoint may return an error status","Raw HTML too large to process within service limits — truncation or error response","mode=budget used without a query parameter — BM25 ranking may default or fail","max_tokens set below minimum of 20 — validation error","Payment not authorized or x402 flow fails — billing error preventing execution","URL contains paywalled or bot-blocked content — distillation returns empty or partial data"],"whenToPreferThis":"Choose this endpoint when you need to feed live web content into an LLM or RAG pipeline while aggressively controlling token usage. It is especially valuable when you already have a raw HTML string to process directly, when you need BM25-ranked focused excerpts rather than full-page summaries, or when you want built-in ROI reporting on token savings. Prefer it over generic web scrapers when token budget enforcement and multiple distillation modes (Markdown, structured, skeleton, budget) are needed in a single API call.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:26.223Z","isFirstParty":false,"canonicalSlug":"preflight-agentdiet-dev-agentdiet-rag-chunk-web-url-distillation-d7cf7509"}