{"uid":"cap_g3UTgul_Mm6wD62DKkorm","slug":"shopify-intel-agentdiet-dev-web-url-context-distiller-bm25-budget-5759a507","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://shopify-intel.agentdiet.dev/v1/context-bloat-eliminator)","url":"https://shopify-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_ruy_3EASTxc-Y2L0GMfDE","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"shopify-intel.agentdiet.dev","brandSlug":"shopify-intel-agentdiet-dev-mpp","brandBaseUrl":"https://shopify-intel.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or raw HTML and compresses it into compact, agent-ready tokens using markdown, structured, skeleton, or BM25-budget extraction modes","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into compact markdown, using budget mode focused on 'payment intents' with a strict ceiling of 500 tokens, so I can feed just the relevant content to my LLM without blowing my context window.","exampleUseCases":[{"title":"Token-efficient doc ingestion for agent","prompt":"Pull https://docs.openai.com/api-reference and distill it into structured mode — I want clean JSON tables and metadata so my agent can reference the API without eating up my entire context window."},{"title":"BM25 query-focused excerpt for research","prompt":"Fetch https://en.wikipedia.org/wiki/Retrieval-augmented_generation and give me only the parts relevant to 'chunking strategies', using budget mode with a 300-token ceiling."},{"title":"Skeleton outline of a competitor page","prompt":"Distill https://anthropic.com/claude into skeleton mode so I can see the page structure and headings without all the filler text."}],"resultDescription":"Returns a distilled payload (markdown, structured JSON tables/metadata, skeleton outline, or BM25-ranked budget excerpt) along with ROI proof metrics including raw vs. distilled token counts, compression ratio percentage, tokens saved, and estimated LLM cost saved in USD. Also includes cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns fetch error","HTML too large or malformed may produce incomplete distillation","mode=budget without a query or max_tokens may fall back to default behavior","Rate limiting or payment failure (402) blocks the call","Paywalled or JavaScript-heavy pages may return sparse content","builtin:// scheme only works for recognized built-in doc targets like stripe-docs"],"whenToPreferThis":"Choose this endpoint when you need to feed web content to an LLM but want to minimize token consumption and cost. It is especially valuable when the source page is long, noisy, or filled with boilerplate, and you only need semantically relevant excerpts (use mode=budget with a BM25 query). Prefer it over raw scraping when your pipeline has a strict token budget or when you want structured extraction (tables, metadata) rather than raw HTML.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:07.726Z","isFirstParty":false,"canonicalSlug":"shopify-intel-agentdiet-dev-web-url-context-distiller-bm25-budget-5759a507"}