{"uid":"cap_h8o7oZcxQhnkk-fHZQSmp","slug":"polymarket-odds-agentdiet-dev-web-url-distiller-with-bm25-budget-1d4f6aeb","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/rag-token-diet)","url":"https://polymarket-odds.agentdiet.dev/v1/rag-token-diet?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_vHsC_3h5mTxflHDi-L0r6","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 web URL (or accepts raw HTML) and compresses it into compact, agent-ready tokens using configurable distillation modes including BM25-focused budget excerpts","exampleAgentPrompt":"Distill the URL https://stripe.com/docs/payments/accept-a-payment into compact markdown using budget mode, focused on the query 'payment intent setup', with a max of 500 tokens.","exampleUseCases":[{"title":"RAG pipeline token budget enforcement","prompt":"Fetch https://openai.com/research/gpt-4 and compress it to no more than 300 tokens in budget mode, focused on the query 'model capabilities benchmarks' — I need it ready to feed into my retrieval pipeline without blowing my context window."},{"title":"Structured data extraction from docs page","prompt":"Pull the page at https://docs.stripe.com/api/charges and distill it into structured mode so I get the tables and metadata as clean JSON — I'm building a reference sheet for our billing integration."},{"title":"Quick skeleton outline for research","prompt":"Give me a skeleton outline of https://en.wikipedia.org/wiki/Large_language_model so I can see the high-level structure and section headings before deciding which parts to read in full."}],"resultDescription":"Returns a distilled representation of the webpage (markdown, structured JSON, skeleton, or BM25 budget excerpt) alongside ROI proof metrics including raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Also includes cache status and billing details.","failureModes":["Invalid or unreachable URL returns a fetch error","max_tokens below minimum of 20 is rejected","mode=budget without a query may produce unoptimized results","Raw HTML input ignored if URL is also supplied and conflicts","Rate limiting or payment failure via x402 returns 402 status","Paywalled or JavaScript-heavy pages may yield incomplete distillation"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM context window efficiently, especially when token costs matter. It excels over plain scraping when you need BM25-focused relevance trimming (budget mode), structured table extraction, or skeleton outlines. Prefer it over generic scrapers when you need built-in ROI metrics showing compression gains. Ideal for RAG pipelines, agent research tasks, and any workflow where raw HTML would be too token-expensive to process directly.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:24:13.827Z","isFirstParty":false,"canonicalSlug":"polymarket-odds-agentdiet-dev-web-url-distiller-with-bm25-budget-9b5a3fa8"}