{"uid":"cap_B2MqmJBVru2C1vAHrFVSN","slug":"token-intel-agentdiet-dev-web-content-distillation-with-bm25-budget-d0ecea1f","name":"Web Content Distillation 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://token-intel.agentdiet.dev/v1/context-compress)","url":"https://token-intel.agentdiet.dev/v1/context-compress?utm_source=zero.xyz","method":"POST","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_3PiSWNpEQSblu-BjD33Tb","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"token-intel.agentdiet.dev","brandSlug":"token-intel-agentdiet-dev-mpp","brandBaseUrl":"https://token-intel.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and compresses a URL or raw HTML into Markdown, structured JSON, skeleton outline, or a BM25-ranked token-budget excerpt optimized for LLM consumption.","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it into clean Markdown using budget mode, focusing on 'payment intents' and keeping it under 2000 tokens — I need to see how many tokens we're saving.","exampleUseCases":[{"title":"Fit long docs into agent context","prompt":"Grab https://docs.openai.com/api-reference and compress it into budget mode focused on 'function calling', capped at 3000 tokens — show me the compression ratio and tokens saved."},{"title":"Convert product page to structured data","prompt":"Take https://www.notion.so/product and distill it in structured mode so I get the tables and metadata as JSON — I want to see pricing tiers and feature lists pulled out cleanly."},{"title":"Summarize a competitor's blog post","prompt":"Distill https://anthropic.com/news/claude-3 into Markdown mode and give me a skeleton outline of the article so I can quickly scan the main sections without reading the whole thing."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt), plus an 'roi_proof' block showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes cache status (HIT/MISS) and billing details.","failureModes":["URL is unreachable or returns non-200 — endpoint cannot fetch and will return an error status","HTML payload is empty or malformed — distillation returns empty or minimal output","max_tokens set too low (below 20) — rejected with validation error","mode=budget used without a query — BM25 ranking has no focus signal, may return degraded results","Payment not provided or fails — x402 payment required error before processing","Rate limit or timeout on the target URL — fetch failure propagated in response"],"whenToPreferThis":"Choose this endpoint when you need to reduce token consumption from web pages or HTML before passing content to an LLM, especially when working with strict context windows or cost budgets. The BM25 budget mode is uniquely valuable when you have a specific query and want only the most relevant passages within a hard token ceiling. Prefer this over generic scrapers when you need built-in ROI proof (tokens saved, cost saved) and multiple distillation modes (Markdown, structured, skeleton, budget) in a single call priced at $0.001.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:31:07.345Z","isFirstParty":false,"canonicalSlug":"token-intel-agentdiet-dev-web-content-distillation-with-bm25-budget-d0ecea1f"}