{"uid":"cap_xwa2l0BrvCqoEZsxv1emS","slug":"onchain-risk-agentdiet-dev-web-url-distiller-with-bm25-budget-control-1ba293a4","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://onchain-risk.agentdiet.dev/v1/rag-chunk)","url":"https://onchain-risk.agentdiet.dev/v1/rag-chunk?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_T63Lj8R92wjcPLBnYSlOv","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 URL or raw HTML and distills it into compact, agent-ready tokens using markdown, structured, skeleton, or BM25-budget extraction modes","exampleAgentPrompt":"Distill the content at https://docs.stripe.com/payments/payment-intents into compact markdown with a token budget of 500 tokens, focused on the query 'payment confirmation flow'.","exampleUseCases":[{"title":"RAG pipeline cost reduction","prompt":"Fetch https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) and distill it down to at most 300 tokens using budget mode, focused on the query 'attention mechanism', so I can pass it cheaply into my RAG pipeline."},{"title":"Structured data extraction from docs page","prompt":"Pull the page at https://docs.openai.com/api-reference/chat and extract all structured tables and metadata from it in structured mode so I can parse the fields programmatically."},{"title":"Quick skeleton outline of article","prompt":"Get me a skeleton outline of https://techcrunch.com/2024/05/01/ai-agents-rise so I can see the main headings and sections without reading the whole thing."}],"resultDescription":"Returns a distilled representation of the target URL in the chosen mode (markdown, structured JSON tables/metadata, skeleton outline, or BM25-focused budget excerpt), along with ROI proof metrics including raw token count, distilled token count, tokens saved, compression ratio percentage, LLM cost saved in USD, and cache hit/miss status.","failureModes":["URL unreachable or returns non-200 status — endpoint may return an error status","URL paywall or bot-blocking — content cannot be fetched","max_tokens too small to produce meaningful output — may return truncated or minimal content","Invalid mode enum value — returns validation error","BM25 query missing when mode=budget — may return unfiltered or error","Payment failure via x402 — call not processed if USDC payment not completed"],"whenToPreferThis":"Choose this endpoint when you need to pass web content into an LLM context window efficiently and cost-effectively, especially when token budget is a concern. Ideal for RAG pipelines, agent research workflows, or any scenario where you need structured or compressed web content with measurable token savings. Prefer the budget mode with a BM25 query when you want topically focused extraction rather than full-page distillation.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:24:18.223Z","isFirstParty":false,"canonicalSlug":"onchain-risk-agentdiet-dev-web-url-distiller-with-bm25-budget-control-1ba293a4"}