{"uid":"cap_BB93VAJo8vca8G3Fa-K8S","slug":"prompt-guard-agentdiet-dev-agentdiet-web-distiller-with-bm25-budget-b4edb49d","name":"AgentDiet Web 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://prompt-guard.agentdiet.dev/api/diet)","url":"https://prompt-guard.agentdiet.dev/api/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_Z0CTYjErlurqwBN5DHTFq","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"prompt-guard.agentdiet.dev","brandSlug":"prompt-guard-agentdiet-dev-mpp","brandBaseUrl":"https://prompt-guard.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into compressed Markdown, structured JSON, skeleton outline, or BM25-ranked token-budget excerpts for LLM consumption.","exampleAgentPrompt":"Distill https://stripe.com/docs/payments/accept-a-payment into clean markdown using budget mode, focusing on 'payment intent setup', and keep it under 800 tokens.","exampleUseCases":[{"title":"Token-efficient webpage summarization for LLM","prompt":"Fetch and distill https://openai.com/research/gpt-4 into markdown so I can feed it to my LLM without blowing my context window — use budget mode with a 600-token ceiling and focus the BM25 query on 'multimodal capabilities'."},{"title":"Structured data extraction from e-commerce page","prompt":"Distill this product page https://www.apple.com/shop/buy-iphone into structured JSON so I can pull out the product names, prices, and variants without wading through all the HTML noise."},{"title":"Skeleton outline for research navigation","prompt":"Give me a skeleton outline of https://arxiv.org/abs/2303.08774 so I can quickly see the section headers and decide which parts of the paper are worth reading in full."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown string, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes cache status (HIT/MISS), billing details, and overall status ('ok').","failureModes":["URL unreachable or returns non-200 — distillation cannot proceed","HTML payload too large or malformed — parser may fail or return partial content","max_tokens set below minimum of 20 — validation error","mode=budget without a query — BM25 scoring has no focus, may return degraded results","Payment not authorized (HTTP 402) — request blocked until x402 payment is resolved","Invalid URL format — schema validation error on 'url' field"],"whenToPreferThis":"Choose this endpoint when you need to feed web content to an LLM but want to minimize token usage and cost — especially when you have a strict context window, a specific focus query for BM25 relevance filtering, or need structured/skeleton output rather than raw HTML. It is superior to generic scrapers when ROI accounting and token compression metrics matter to your agent pipeline.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:34:03.229Z","isFirstParty":false,"canonicalSlug":"prompt-guard-agentdiet-dev-agentdiet-web-distiller-with-bm25-budget-b4edb49d"}