{"uid":"cap_zEXsEJia0FcMnxqao4S_i","slug":"prompt-guard-agentdiet-dev-web-url-html-distiller-with-bm25-budget-e20b3656","name":"Web URL & HTML 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/v1/context-diet)","url":"https://prompt-guard.agentdiet.dev/v1/context-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_xGojWa3qhqbtjjk06r1Zk","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 compresses a URL or raw HTML into compact, agent-ready tokens using configurable distillation modes including BM25-ranked budget-constrained excerpts","exampleAgentPrompt":"Can you distill https://docs.stripe.com/api into compact markdown using budget mode, focused on 'payment intents', and keep it under 500 tokens?","exampleUseCases":[{"title":"Compress docs page for agent context","prompt":"Distill https://platform.openai.com/docs/api-reference into structured markdown so I can pass the key details to my agent without blowing up the context window."},{"title":"BM25 focused excerpt from long article","prompt":"I need you to fetch https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) and give me only the most relevant sections about 'attention mechanism' — keep it under 300 tokens using budget mode."},{"title":"Extract tables from raw HTML snippet","prompt":"Here's a big chunk of raw HTML from a financial report — can you distill it into structured JSON tables and pull out the metadata, ignoring all the navigation and boilerplate?"}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown, structured JSON, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' block showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Also includes optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 HTTP status — endpoint may return an error status","HTML payload is empty or malformed — distillation may return minimal or empty data","Token budget (max_tokens) too low relative to content — may truncate critical content","BM25 query provided without mode=budget — query may be ignored","Rate limiting or payment failure via x402 — request rejected without billing","Idempotency-Key collision on differing payloads — undefined behavior"],"whenToPreferThis":"Choose this endpoint when you need to reduce LLM context costs by compressing web pages or HTML documents before passing them to a language model, especially when you have a strict token budget or want BM25-ranked relevance filtering. It is particularly valuable when dealing with long documentation pages, financial filings, or content-heavy sites where only a subset is relevant to a given query. Prefer this over generic scrapers when token efficiency and ROI measurement matter.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T12:35:07.820Z","isFirstParty":false,"canonicalSlug":"prompt-guard-agentdiet-dev-web-url-html-distiller-with-bm25-budget-e20b3656"}