{"uid":"cap_mYd8UDFjlN3b0RW-GpDxT","slug":"polymarket-odds-agentdiet-dev-web-url-distiller-with-bm25-budget-9b5a3fa8","name":"Web URL Distiller 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://polymarket-odds.agentdiet.dev/v1/web-scrape)","url":"https://polymarket-odds.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_pYKKpNDb6Ln-weeyHWLOI","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"polymarket-odds.agentdiet.dev","brandSlug":"polymarket-odds-agentdiet-dev-mpp","brandBaseUrl":"https://polymarket-odds.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL (or accepts raw HTML) and distills its content into compact, agent-ready tokens using configurable extraction modes and BM25 keyword-focused budget control","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments into clean markdown, keeping it under 1000 tokens and focusing on the query 'payment intent lifecycle' — I want the budget mode.","exampleUseCases":[{"title":"Research page within tight token budget","prompt":"Fetch https://openai.com/research/gpt-4 and distill it into under 500 tokens using budget mode, focusing on the query 'model capabilities and benchmarks' so I don't blow my context window."},{"title":"Extract structured data tables from a site","prompt":"Pull the structured tables and metadata from https://fred.stlouisfed.org/series/GDP using structured mode so I can parse the economic data cleanly."},{"title":"Convert documentation page to markdown","prompt":"Scrape https://docs.anthropic.com/claude/reference/getting-started-with-the-api and give me a clean markdown version of the content so my agent can read the API docs without loading raw HTML."}],"resultDescription":"Returns a 'data' object containing the distilled content (markdown, structured JSON tables/metadata, skeleton outline, or BM25 budget excerpt depending on mode), plus an roi_proof object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd, along with cache status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","max_tokens set below 20 is rejected by schema validation","mode=budget without a query may produce unfocused output","Raw HTML too large may exceed processing limits","Paywalled or JavaScript-heavy pages may yield incomplete content","HTTP 402 payment required if agent lacks valid x402 payment credentials"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read webpage content but must stay within a token budget, or when raw HTML is too large and noisy for direct consumption. Especially valuable when BM25 keyword-focused extraction is needed to pull only the most relevant passages from a long page, or when you need structured tables/metadata rather than raw HTML. Prefer over generic scraping tools when token cost optimization and compression ratio reporting are important.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:06.919Z","isFirstParty":false,"canonicalSlug":"polymarket-odds-agentdiet-dev-web-url-distiller-with-bm25-budget-9b5a3fa8"}