{"uid":"cap_o83LwfVOHgRLw2VI0hMrh","slug":"shopify-intel-agentdiet-dev-web-url-context-compressor-with-bm25-0f44fe0f","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://shopify-intel.agentdiet.dev/v1/context-compress)","url":"https://shopify-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_8LAJWzjmScd6azKutRVCy","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 and distills a web URL or raw HTML into compact, agent-ready tokens using multiple extraction modes including BM25-focused budget compression","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into compact markdown using budget mode, focused on 'payment intents', and keep it under 500 tokens so I can fit it in my context window.","exampleUseCases":[{"title":"Token-budget extraction for RAG pipeline","prompt":"Fetch https://openai.com/research/gpt-4 and distill it into markdown keeping it under 300 tokens — I only care about content related to 'model architecture'."},{"title":"Structured data scrape for competitor research","prompt":"Pull https://shopify.com/pricing and convert it to structured JSON tables so I can compare their pricing tiers without reading through all the page noise."},{"title":"Skeleton outline for long documentation page","prompt":"Distill https://docs.aws.amazon.com/lambda/latest/dg/welcome.html into a skeleton outline so I can quickly see the top-level structure before diving into the full docs."}],"resultDescription":"Returns a 'data' object containing the distilled content (markdown, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt), along with an 'roi_proof' block showing raw vs distilled token counts, tokens saved, compression ratio percentage, LLM cost saved in USD, and ROI multiplier. Also includes optional cache status (HIT/MISS) and billing details.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error status","Raw HTML exceeds processing limits — may fail or truncate silently","mode=budget used without a query parameter — BM25 ranking may be unfocused","max_tokens set below 20 — rejected by schema validation","Invalid or malformed URL — returns error status","Rate limiting or payment failure via x402 — HTTP 402 returned"],"whenToPreferThis":"Choose this endpoint when you need to feed web page content into an LLM but want to minimize token consumption, especially with the 'budget' mode and BM25 query focusing. It is ideal over generic scrapers when you need quantified ROI proof of compression savings, need multiple output formats (markdown, structured, skeleton), or are working within strict context-window constraints. Particularly suited for agent pipelines that need to process many URLs cost-efficiently.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:20:49.482Z","isFirstParty":false,"canonicalSlug":"shopify-intel-agentdiet-dev-web-url-context-compressor-with-bm25-0f44fe0f"}