{"uid":"cap_xKyujjt5u--mxw2U14-HC","slug":"preflight-agentdiet-dev-web-url-html-prompt-compressor-with-bm25-c7250e13","name":"Web URL & HTML Prompt Compressor 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://preflight.agentdiet.dev/v1/prompt-compress)","url":"https://preflight.agentdiet.dev/v1/prompt-compress?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_05GTo2VdSEpcPy5mYntor","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"preflight.agentdiet.dev","brandSlug":"preflight-agentdiet-dev-mpp","brandBaseUrl":"https://preflight.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-focused budget modes","exampleAgentPrompt":"Grab the Stripe documentation page at https://stripe.com/docs/payments and distill it into markdown, keeping it under 800 tokens focused on the query 'payment intents'.","exampleUseCases":[{"title":"Fit docs into context window","prompt":"Take this URL for the OpenAI API reference — https://platform.openai.com/docs/api-reference — and compress it into structured mode so I can include the key tables and metadata in my prompt without blowing my context limit."},{"title":"BM25-focused competitor research","prompt":"Fetch https://www.anthropic.com/research and distill it in budget mode with the query 'safety alignment' and a max of 500 tokens — I only want the parts most relevant to AI safety."},{"title":"Turn raw HTML into clean markdown","prompt":"I've got the raw HTML from a scraped product page — can you run it through the markdown distiller so my agent gets a clean, readable version without all the nav clutter and scripts?"}],"resultDescription":"Returns a distilled 'data' object containing the page content in the requested format (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt), 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 cache status (HIT/MISS) and billing details.","failureModes":["URL is unreachable or returns a non-200 response — endpoint may return an error status","Token budget too low (max_tokens < 20) — rejected by schema validation","BM25 query provided without mode=budget — query parameter silently ignored","Raw HTML is empty or malformed — may produce minimal or empty distillation output","Rate limit or payment failure via x402 — billing error returned instead of data"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to fetch and condense web content to fit within a strict LLM context window, especially when you need BM25-relevance filtering to surface only query-relevant passages. Prefer it over generic scrapers when token economy matters — the built-in ROI proof lets agents verify compression gains. Use mode=budget when you have a hard token ceiling, mode=structured for tabular/metadata extraction, mode=skeleton for outline navigation, and mode=markdown for general clean text distillation.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:26:17.253Z","isFirstParty":false,"canonicalSlug":"preflight-agentdiet-dev-web-url-html-prompt-compressor-with-bm25-c7250e13"}