{"uid":"cap_Jz0UPdvy3O4NhdOqvbwGQ","slug":"cve-intel-agentdiet-dev-web-url-context-compressor-with-bm25-budget-08875cd3","name":"Web URL Context 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://cve-intel.agentdiet.dev/v1/context-compress)","url":"https://cve-intel.agentdiet.dev/v1/context-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_0CvCrjUjSh2WXIglMARH7","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"cve-intel.agentdiet.dev","brandSlug":"cve-intel-agentdiet-dev-mpp","brandBaseUrl":"https://cve-intel.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or raw HTML and distills it into compact, agent-ready tokens using configurable extraction modes and optional BM25-ranked token budgeting","exampleAgentPrompt":"Distill this URL into compact markdown for my context window — https://stripe.com/docs/payments/accept-a-payment — use budget mode with the query 'payment intent setup' and cap it at 500 tokens.","exampleUseCases":[{"title":"Compress documentation page for LLM ingestion","prompt":"Fetch and compress https://docs.openai.com/api-reference/chat into agent-ready markdown — I want structured mode so I get the tables and metadata cleanly without blowing my context window."},{"title":"Budget-capped extraction for a research query","prompt":"Pull this Wikipedia article on transformer neural networks — https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) — and give me only the parts relevant to 'self-attention mechanism' in budget mode, max 300 tokens."},{"title":"Skeleton outline of a long report page","prompt":"Take this SEC filing page — https://www.sec.gov/cgi-bin/browse-edgar?action=getcompany — and give me a skeleton outline so I can see the structure without reading the whole thing."}],"resultDescription":"Returns a distilled representation of the webpage in the requested format (markdown, structured JSON with tables/metadata, skeleton outline, or BM25-ranked budget excerpt), along with an ROI proof object showing raw vs. distilled token counts, compression ratio, tokens saved, estimated LLM cost saved, and optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 — fetch failure error","URL points to non-HTML content (PDF, binary) — parsing may fail or return empty","max_tokens set below 20 — validation error","BM25 query provided without mode=budget — query may be ignored","Raw HTML string too large — may hit payload limits","Invalid mode enum value — returns 400 validation error","Paid endpoint — insufficient payment returns HTTP 402"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read a webpage but must stay within a token budget, reduce LLM inference costs, or extract only query-relevant content via BM25 ranking. It is especially valuable for long documentation pages, research articles, or any HTML payload where full ingestion would be prohibitively expensive. Prefer it over raw web scraping when you need both fetching and compression in a single call, and when you need measurable ROI proof (tokens saved, cost saved) returned alongside the content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:45:43.941Z","isFirstParty":false,"canonicalSlug":"cve-intel-agentdiet-dev-web-url-context-compressor-with-bm25-budget-08875cd3"}