{"uid":"cap_DFBvgyNic1U8JZ0gHY5VG","slug":"hn-pulse-agentdiet-dev-web-url-distillation-to-compact-agent-ready-7691ae44","name":"Web URL Distillation to Compact Agent-Ready Tokens","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://hn-pulse.agentdiet.dev/v1/pdf-extract)","url":"https://hn-pulse.agentdiet.dev/v1/pdf-extract?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_gyd4TEvZ3Sk9sXhaqvn_E","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"hn-pulse.agentdiet.dev","brandSlug":"hn-pulse-agentdiet-dev-mpp","brandBaseUrl":"https://hn-pulse.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a webpage by URL (or accepts raw HTML) and distills it into compact, agent-ready Markdown, structured JSON, outline skeleton, or BM25-focused budget excerpts with token savings metrics.","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments into compact markdown, keeping it under 2000 tokens, focused on payment intents.","exampleUseCases":[{"title":"Budget-aware API docs extraction","prompt":"Grab the OpenAI API docs at https://platform.openai.com/docs/api-reference and distill them into budget mode focused on 'embeddings', capped at 1500 tokens so I can fit them in my context window."},{"title":"Structured data extraction from news article","prompt":"Fetch the article at https://techcrunch.com/2024/01/15/openai-funding and pull out all the structured tables and metadata as JSON — I need it in structured mode."},{"title":"Skeleton outline of long research paper","prompt":"Take this URL https://arxiv.org/abs/2310.06825 and give me a skeleton outline of the document so I can quickly understand the structure before deciding whether to read the full thing."}],"resultDescription":"Returns a 'data' object containing distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-filtered excerpt depending on mode), along with an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, ROI multiplier, and estimated LLM cost saved in USD. Also includes optional cache status (HIT/MISS) and billing info.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error status","max_tokens ceiling too low to produce meaningful output — truncation or error","Raw HTML too large to process within service limits","BM25 query returns no relevant sections when mode=budget — sparse or empty excerpt","Payment/402 flow fails if agent lacks sufficient USDC balance","Invalid mode enum value causes validation error"],"whenToPreferThis":"Choose this endpoint when you need to fit web content into a constrained LLM context window, want BM25-focused relevance filtering around a specific query, or need structured/skeleton extraction rather than raw scraping. Ideal for agentic pipelines that repeatedly fetch web pages and want to minimize token costs. Prefer over generic scrapers when token budget control and compression metrics matter.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:26:06.672Z","isFirstParty":false,"canonicalSlug":"hn-pulse-agentdiet-dev-web-url-distillation-to-compact-agent-ready-7691ae44"}