{"uid":"cap_37Z5EkBiWTJvXbih3eY7v","slug":"arxiv-digest-agentdiet-dev-web-url-distillation-with-bm25-budget-4c67bf4b","name":"Web URL Distillation 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://arxiv-digest.agentdiet.dev/v1/web-scrape)","url":"https://arxiv-digest.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_30wM5ryGx_T7CUqJQHj9c","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"arxiv-digest.agentdiet.dev","brandSlug":"arxiv-digest-agentdiet-dev-mpp","brandBaseUrl":"https://arxiv-digest.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and compresses a web page or raw HTML into compact, agent-ready tokens using configurable distillation modes including BM25-focused budget extraction","exampleAgentPrompt":"Distill https://arxiv.org/abs/2406.12345 into compact markdown — use budget mode with the query 'transformer attention mechanism' and cap it at 500 tokens.","exampleUseCases":[{"title":"Research paper extraction for agents","prompt":"Fetch https://arxiv.org/abs/2312.00752 and distill it into structured markdown so I can feed just the key content into my LLM without blowing my token budget."},{"title":"Query-focused snippet from documentation","prompt":"I need you to pull https://docs.stripe.com/payments/payment-intents and extract only the parts relevant to 'webhook event handling' — use budget mode and keep it under 300 tokens."},{"title":"Page skeleton for navigation planning","prompt":"Grab https://en.wikipedia.org/wiki/Artificial_intelligence and give me a skeleton outline of the page structure so I can decide which sections to read in full."}],"resultDescription":"Returns a distilled representation of the webpage in one of four formats: Markdown (readable prose), structured (JSON tables and metadata), skeleton (outline of page structure), or budget (BM25-ranked excerpt within a token ceiling). Also includes an ROI proof object showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD, plus cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","max_tokens set below minimum of 20 causes validation failure","BM25 query provided without mode=budget may be ignored","Raw HTML too large may exceed processing limits","Payment failure via x402 blocks the request","Cache miss on first fetch may increase latency"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read web pages efficiently without consuming excessive tokens — especially useful in agentic pipelines where LLM context is scarce or costly. Prefer this over raw HTTP fetching when you need automatic compression, BM25-focused relevance filtering, or structured extraction from messy HTML. Ideal for research agents, documentation readers, and any workflow where token budget control is critical.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:50:12.911Z","isFirstParty":false,"canonicalSlug":"arxiv-digest-agentdiet-dev-web-url-distillation-with-bm25-budget-4c67bf4b"}