{"uid":"cap_sCr7ZFT00KzdLWgEi39ID","slug":"cve-intel-agentdiet-dev-web-url-context-distiller-bm25-budget-control-c30e046e","name":"Web URL Context Distiller (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-bloat-eliminator)","url":"https://cve-intel.agentdiet.dev/v1/context-bloat-eliminator?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_NFU1ma4-xN5sAnRRiZbvi","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 webpage or raw HTML and compresses it into compact, agent-ready tokens using configurable distillation modes including BM25-focused budget extraction","exampleAgentPrompt":"Fetch https://stripe.com/docs/api and distill it into compact markdown within a 500-token budget, focusing on the query 'authentication headers'.","exampleUseCases":[{"title":"Compress documentation before LLM reasoning","prompt":"Grab the page at https://docs.openai.com/api-reference and compress it into a skeleton outline under 300 tokens so I can include it in my next prompt without blowing my context window."},{"title":"BM25 relevance-filtered research extraction","prompt":"Distill https://arxiv.org/abs/2310.06825 in budget mode with the query 'retrieval augmented generation benchmarks' and keep it under 400 tokens — I only want the parts relevant to my query."},{"title":"Structured data extraction from a webpage","prompt":"Pull the page at https://en.wikipedia.org/wiki/List_of_S%26P_500_companies and give me the content in structured mode so I get clean JSON tables instead of raw HTML."}],"resultDescription":"Returns a distilled representation of the fetched webpage or HTML — either clean Markdown, structured JSON tables/metadata, a skeleton outline, or a BM25-focused budget excerpt — along with ROI proof metrics including raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved. Also includes cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","mode=budget without a query or max_tokens may produce unconstrained output","Very large pages may hit internal processing limits","HTML payloads with heavy JavaScript rendering may not distill fully","max_tokens below 20 is rejected by schema validation","Payment failure via x402 blocks execution"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web content but must stay within a token budget or reduce LLM costs. Especially useful when a documentation page, article, or HTML blob is too verbose to pass directly into a prompt. The BM25 budget mode is ideal when only query-relevant passages are needed from a large page. Prefer over general-purpose scrapers when you specifically need token-optimized, agent-ready output with compression metrics.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:51:36.573Z","isFirstParty":false,"canonicalSlug":"cve-intel-agentdiet-dev-web-url-context-distiller-bm25-budget-control-c30e046e"}