{"uid":"cap_9iMTUgWQYEIQLKHo5XU0H","slug":"polymarket-odds-agentdiet-dev-web-url-dom-distiller-bm25-budget-mode-81604c10","name":"Web URL DOM Distiller (BM25 Budget Mode)","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/dom-stripper)","url":"https://polymarket-odds.agentdiet.dev/v1/dom-stripper?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_I62zQFs7apOmZ9KZ8504X","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 webpage or accepts raw HTML and distills it into compact, agent-ready tokens using Markdown, structured, skeleton, or BM25-focused budget extraction modes.","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments/checkout into compact Markdown using budget mode, with a focus query of 'payment session creation' and a max token limit of 800 tokens.","exampleUseCases":[{"title":"LLM cost reduction from live webpage","prompt":"Fetch https://openai.com/blog/gpt-4o and compress it into clean Markdown under 500 tokens — I want to feed just the relevant content to my LLM without blowing my token budget."},{"title":"Structured data extraction from HTML","prompt":"I have the raw HTML of a product listing page — can you distill it into structured JSON tables so I can extract the pricing and specs without parsing all the noise myself?"},{"title":"Skeleton outline of documentation site","prompt":"Give me a skeleton outline of https://docs.anthropic.com/en/docs/about-claude/models/overview so I can quickly see the page structure before deciding which section to read in full."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused 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. Also includes optional cache hit/miss metadata and billing details.","failureModes":["Invalid or unreachable URL returns an error status","HTML payload too large may exceed processing limits","mode=budget without a query or max_tokens may fall back to defaults","Rate limiting or payment failure (HTTP 402) blocks the request","Paywalled or JavaScript-rendered pages may yield incomplete distillation","max_tokens set below 20 is rejected by schema validation"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read web content but must stay within a token budget, reduce LLM API costs, or receive clean structured output rather than raw HTML. Especially useful in agentic pipelines where raw webpage fetching is too token-expensive. The BM25 budget mode makes it uniquely suited for relevance-focused extraction when only a portion of a page is relevant to the agent's current query. Prefer over generic scrapers when you need built-in compression metrics and LLM cost accounting.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:41.719Z","isFirstParty":false,"canonicalSlug":"polymarket-odds-agentdiet-dev-web-url-dom-distiller-bm25-budget-mode-81604c10"}