{"uid":"cap_SbPB_6thGqHOvswjT55YU","slug":"mesh-agentdiet-dev-web-url-distillation-bm25-token-budget-rag-fff95c11","name":"Web URL Distillation & BM25 Token-Budget RAG Preprocessor","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://mesh.agentdiet.dev/v1/rag-token-diet)","url":"https://mesh.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_JvHL2sqsaKf2s5VL6EFDe","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"mesh.agentdiet.dev","brandSlug":"mesh-agentdiet-dev-mpp","brandBaseUrl":"https://mesh.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and compresses a web page (or raw HTML) into compact, agent-ready tokens using multiple distillation modes including BM25-focused budget extraction","exampleAgentPrompt":"Can you fetch https://docs.stripe.com/api and distill it into compact markdown, keeping it under 800 tokens and focusing on the authentication section?","exampleUseCases":[{"title":"RAG pipeline cost reduction","prompt":"Pull the content from https://openai.com/research/gpt-4 and distill it into budget mode with a max of 500 tokens, focused on the query 'model capabilities and benchmarks' — I want to use it as context without blowing my token budget."},{"title":"Documentation skeleton for agent navigation","prompt":"Fetch https://docs.anthropic.com/claude and give me a skeleton outline of the page so I can see the high-level structure before deciding which sections to read in full."},{"title":"Structured data extraction from a product page","prompt":"Distill https://stripe.com/pricing into structured mode so I get the pricing tiers and features as a clean JSON table I can compare programmatically."}],"resultDescription":"Returns a 'data' object containing the distilled content (markdown text, structured JSON tables, skeleton outline, or BM25-focused excerpt depending on mode), plus an ROI proof block showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd. Also includes cache status (HIT/MISS) and optional billing details.","failureModes":["URL is unreachable or returns non-200 — distillation fails with a fetch error","URL points to a binary/non-HTML resource (PDF, image) — may return empty or garbled output","max_tokens too small (below 20) — rejected by schema validation","mode=budget used without a query — BM25 focus cannot operate, may fall back or error","Raw HTML provided is malformed — distillation quality degrades","Payment not settled (x402 flow) — 402 response returned before processing begins","Cached stale content returned — cache HIT may reflect older page version"],"whenToPreferThis":"Choose this endpoint when you need to feed live web content into an LLM context window cost-efficiently — especially when the raw page is large and token budget matters. It is distinctly useful for RAG pipelines, agent research tasks, and documentation ingestion where BM25 relevance filtering or structured extraction reduces noise. Prefer over generic scrapers when token savings and compression ROI metrics are needed, or when you want multiple distillation modes (markdown, structured, skeleton, budget) in a single call.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:41.835Z","isFirstParty":false,"canonicalSlug":"mesh-agentdiet-dev-web-url-distillation-bm25-token-budget-rag-fff95c11"}