{"uid":"cap_LkVY5PVftzbQnyMVYQCyC","slug":"llms-generator-agentdiet-dev-web-url-context-distiller-bm25-budget-f1cca1be","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://llms-generator.agentdiet.dev/v1/context-bloat-eliminator)","url":"https://llms-generator.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_DfgX6XilQpTaEkOWBKHLW","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"llms-generator.agentdiet.dev","brandSlug":"llms-generator-agentdiet-dev-mpp","brandBaseUrl":"https://llms-generator.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a web URL or raw HTML into compact, agent-ready tokens using configurable extraction modes and BM25-based token budget control.","exampleAgentPrompt":"Can you fetch https://docs.stripe.com/api/charges and distill it into compact markdown, keeping it under 500 tokens focused on 'charge creation parameters'?","exampleUseCases":[{"title":"Docs page for LLM context window","prompt":"Grab the Stripe API docs at https://docs.stripe.com/api and distill them into compact markdown under 800 tokens — focus on anything related to 'refund processing'."},{"title":"Structured extraction from a news article","prompt":"Pull this article at https://techcrunch.com/2024/05/01/openai-gpt5 and give me a structured JSON summary with key metadata and tables — I need it agent-ready without all the navigation clutter."},{"title":"Skeleton outline of a long report","prompt":"Take the URL https://reports.weforum.org/global-risks-2024 and extract just the skeleton outline so I can see the section headers and structure without reading the whole thing."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown, structured JSON, skeleton, or BM25 excerpt depending on mode), an 'roi_proof' object showing raw vs. distilled token counts, tokens saved, compression ratio, and estimated LLM cost savings, plus optional cache status and billing details.","failureModes":["URL is unreachable or returns non-200 HTTP status — fetch fails with an error status","URL points to non-HTML content (PDF, binary) that cannot be parsed — may return empty or malformed data","max_tokens too low to produce meaningful output — may return truncated or error response","BM25 query yields no matching sections — budget mode may return minimal content","Raw HTML input is malformed — structured and skeleton modes may produce incomplete output"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest webpage content but must stay within a strict token budget, or when you want BM25-ranked relevance filtering to surface only query-relevant passages from a large page. It is particularly valuable in agentic pipelines where raw page HTML would overflow the context window. Prefer it over generic scrapers when you need token-count metrics and ROI proof of compression.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:35.410Z","isFirstParty":false,"canonicalSlug":"llms-generator-agentdiet-dev-web-url-context-distiller-bm25-budget-f1cca1be"}