{"uid":"cap_Ru7MoCixh2zqe76se4L9k","slug":"agentdiet-dev-distill-url-or-html-with-bm25-budget-control-8f66b30d","name":"Distill URL or HTML 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://agentdiet.dev/v1/rag-diet)","url":"https://agentdiet.dev/v1/rag-diet?utm_source=zero.xyz","method":"POST","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_IkLrHtaoB3a0AOgtye-yf","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"agentdiet.dev","brandSlug":"agentdiet-dev-mpp","brandBaseUrl":"https://agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into compact Markdown, structured JSON, skeleton outlines, or BM25-ranked token-budget excerpts for LLM consumption","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments/accept-a-payment into clean markdown, keeping it under 500 tokens and focusing on the parts about payment intents.","exampleUseCases":[{"title":"Token-efficient RAG pipeline preprocessing","prompt":"Before sending this page to my LLM, distill https://docs.anthropic.com/claude/reference/getting-started-with-the-api into budget mode with the query 'authentication and API keys', capped at 300 tokens — I want to minimize my context costs."},{"title":"Structured table extraction from financial page","prompt":"Pull the content from https://finance.yahoo.com/quote/AAPL and distill it in structured mode so I get the key financial tables and metadata as JSON rather than a wall of HTML."},{"title":"Skeleton outline of long documentation page","prompt":"Give me a skeleton outline of https://kubernetes.io/docs/concepts/overview/ — I just need the heading structure and section summaries, not the full text."}],"resultDescription":"Returns a JSON object containing distilled content (Markdown, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), along with an ROI proof block showing raw vs distilled token counts, compression ratio, tokens saved, estimated LLM cost savings, and ROI multiplier. Also includes cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns an error status","max_tokens below minimum of 20 is rejected with a validation error","BM25 budget mode without a query may return unfiltered or degraded results","HTML payloads that are too large may be truncated or time out","Payment failure via x402 will block execution and return a 402 response","Paywalled or bot-blocked pages may return empty or partial content"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM pipeline at minimal token cost, especially when a strict token budget is required (budget mode with BM25 ranking). It is ideal for RAG preprocessing, agentic web browsing with cost controls, or when you need structured JSON tables extracted from HTML rather than raw text. Prefer it over generic scrapers when token savings, compression metrics, and ROI proof are important signals for your pipeline.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:37:18.103Z","isFirstParty":false,"canonicalSlug":"agentdiet-dev-distill-url-or-html-with-bm25-budget-control-8f66b30d"}