{"uid":"cap_xbGFHN0XHR6j3o2GQX95a","slug":"preflight-agentdiet-dev-web-url-distillation-token-compression-api-344af3f7","name":"Web URL Distillation & Token Compression API","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/web-scrape)","url":"https://preflight.agentdiet.dev/v1/web-scrape?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_Qat_onoKNiTiA5MJq6h9N","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 a webpage or raw HTML and distills it into compact, agent-ready tokens using BM25 budget control and multiple extraction modes","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it into clean markdown, keeping it under 2000 tokens and focusing on the payment intents section.","exampleUseCases":[{"title":"Token-budget research on documentation","prompt":"Grab the OpenAI API docs page at https://platform.openai.com/docs/api-reference and distill it in budget mode focused on 'rate limits', keeping the output under 1500 tokens so I don't blow my context window."},{"title":"Structured data extraction from a landing page","prompt":"Pull https://linear.app/pricing and return it in structured mode so I can see their pricing tiers and features as clean JSON tables — I need to compare plans."},{"title":"Skeleton outline for a long article","prompt":"Fetch this article at https://waitbutwhy.com/2015/01/artificial-intelligence-revolution-1.html and give me just the skeleton outline — I want headings and subheadings only to decide if it's worth reading in full."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton heading outline, or a BM25-focused budget excerpt), plus an roi_proof block showing raw vs distilled token counts, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Also includes a cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns an error status","Token budget too low (max_tokens < 20) rejected by schema validation","mode=budget without a query may return less relevant excerpts","Raw HTML injection via 'html' field may fail if malformed","Rate limiting or payment failure (x402) blocks the request","Paywalled or JavaScript-heavy pages may return minimal content"],"whenToPreferThis":"Choose this endpoint when you need to read a webpage inside an LLM context window without blowing your token budget — especially when you want BM25-focused relevance trimming, structured extraction, or skeleton outlines rather than raw full-page text. It is particularly valuable over generic scraping tools when you need quantified token savings and ROI proof, or when you want to pass a URL to an agent that must stay within strict context limits.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:35.315Z","isFirstParty":false,"canonicalSlug":"preflight-agentdiet-dev-web-url-distillation-token-compression-api-344af3f7"}