{"uid":"cap_5xT4p_2HbKsdm7fEJAeTD","slug":"polymarket-odds-agentdiet-dev-web-url-html-distiller-with-bm25-budget-4bf922b2","name":"Web URL & HTML 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/context-bloat-eliminator)","url":"https://polymarket-odds.agentdiet.dev/v1/context-bloat-eliminator?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_aC17sgnpMxHC3pY2i8XaQ","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 and compresses a webpage URL or raw HTML into compact agent-ready tokens using configurable distillation modes including BM25-focused budget extraction","exampleAgentPrompt":"Can you distill https://stripe.com/docs/api into compact markdown and show me how many tokens were saved versus the raw page?","exampleUseCases":[{"title":"Fit documentation into LLM context","prompt":"Distill https://docs.openai.com/api-reference into structured tables and metadata — I need it compact enough to fit in my context window without losing the key schema details."},{"title":"BM25-focused excerpt for research","prompt":"Fetch https://en.wikipedia.org/wiki/Retrieval-augmented_generation and extract only the parts most relevant to 'vector database indexing', keeping it under 500 tokens using budget mode."},{"title":"Skeleton outline of a long article","prompt":"Give me a skeleton outline of https://www.anthropic.com/research/constitutional-ai so I can quickly understand the structure of the paper without reading the full thing."}],"resultDescription":"Returns a 'data' object containing the distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked 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 details.","failureModes":["URL is unreachable or returns a non-200 HTTP status — endpoint may error or return empty content","HTML payload too large for processing — may hit internal size limits","mode=budget without a query parameter provided — BM25 ranking has no focus signal","max_tokens set below meaningful threshold (minimum 20) — very sparse excerpts","Payment failure via x402 — 402 response requiring USDC payment on Base before content is returned","Rate limiting or bot-blocking by the target URL — distillation fails silently or returns partial content"],"whenToPreferThis":"Choose this endpoint when you need to reduce a large webpage or HTML document to a token-efficient representation before passing it to an LLM, especially when you have a strict token budget. It is particularly valuable when you have a specific focus query and want BM25-ranked relevance filtering rather than naive truncation. Prefer it over generic scrapers when you need ROI metrics (tokens saved, compression ratio) as part of your agent's reasoning. Best suited for single-URL distillation with configurable output modes; not designed for bulk crawling or full-site indexing.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:45:44.751Z","isFirstParty":false,"canonicalSlug":"polymarket-odds-agentdiet-dev-web-url-html-distiller-with-bm25-budget-4bf922b2"}