{"uid":"cap_mJfzgn9gjWAykNRH-Fo7v","slug":"onchain-risk-agentdiet-dev-web-url-distillation-bm25-budget-extractor-22601b41","name":"Web URL Distillation & BM25 Budget Extractor","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://onchain-risk.agentdiet.dev/v1/pdf-extract)","url":"https://onchain-risk.agentdiet.dev/v1/pdf-extract?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_bcliHPZ5ObCDN46hcOuff","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"onchain-risk.agentdiet.dev","brandSlug":"onchain-risk-agentdiet-dev-mpp","brandBaseUrl":"https://onchain-risk.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a webpage URL (or raw HTML) and distills it into compact, agent-ready tokens using configurable modes including BM25-focused budget extraction","exampleAgentPrompt":"Distill https://stripe.com/docs/api into compact markdown for me, using budget mode with a max of 500 tokens and a focus query on 'payment intents'.","exampleUseCases":[{"title":"Compress documentation for LLM context","prompt":"Fetch https://docs.openai.com/api-reference and distill it into structured markdown so I can include the most relevant parts in my agent's context window without burning too many tokens."},{"title":"BM25 focused excerpt from a news article","prompt":"Go to https://techcrunch.com/2024/06/01/ai-agents-rise/ and extract only the sections most relevant to 'autonomous AI agents' using budget mode with a 300 token ceiling."},{"title":"Extract tables and metadata from a financial page","prompt":"Pull https://finance.yahoo.com/quote/AAPL and distill it in structured mode so I get the key data tables and metadata as JSON rather than the full noisy HTML."}],"resultDescription":"Returns a distilled version of the requested webpage or HTML in the chosen format (Markdown, structured JSON, skeleton outline, or BM25 budget excerpt), along with an ROI proof object showing raw vs distilled token counts, tokens saved, compression ratio, and estimated LLM cost savings. Also includes cache status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","Token budget too small (below minimum of 20) causes validation failure","BM25 query not provided when mode=budget may return unfiltered excerpt","Rate limiting or payment failure via x402 may block the request","Raw HTML too large may exceed processing limits","Paywalled or bot-blocked pages may return incomplete content"],"whenToPreferThis":"Choose this endpoint when you need to feed web content to an LLM but want to minimize token usage and cost. It is especially useful when you need BM25-relevance-filtered excerpts within a strict token budget, or when you want structured JSON tables/metadata rather than raw HTML. Prefer it over raw web scraping when compression ratio and LLM cost savings matter, or when you need multiple distillation modes (markdown, structured, skeleton, budget) from a single service.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:12.539Z","isFirstParty":false,"canonicalSlug":"onchain-risk-agentdiet-dev-web-url-distillation-bm25-budget-extractor-22601b41"}