{"uid":"cap_ouaG7rw3nlUdERozRvK15","slug":"token-intel-agentdiet-dev-web-url-context-trimmer-bm25-budget-5b1f719f","name":"Web URL Context Trimmer (BM25 Budget Distillation)","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-trimmer)","url":"https://token-intel.agentdiet.dev/v1/context-trimmer?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_my-JEkreg3ihj72W0Ad93","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 a webpage or accepts raw HTML and distills it into compact, agent-ready tokens using markdown, structured, skeleton, or BM25-budgeted extraction modes","exampleAgentPrompt":"Grab the Stripe docs page at https://stripe.com/docs/payments and distill it into a tight budget excerpt under 500 tokens, focusing on 'refund handling' — I need to keep my context window lean.","exampleUseCases":[{"title":"Token-efficient research briefing","prompt":"Fetch https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) and distill it into clean markdown, keeping it under 800 tokens and focused on the query 'attention mechanism' — I want only the relevant bits for my agent's context."},{"title":"Structured data extraction from landing page","prompt":"Take this URL https://openai.com/pricing and distill it in structured mode so I get tables and metadata about their pricing tiers — I need it in a format my agent can parse easily."},{"title":"Skeleton outline for long-form article","prompt":"Distill https://example.com/very-long-blog-post into a skeleton outline so I can see the section headers and structure without loading thousands of tokens into my prompt."}],"resultDescription":"Returns a JSON object containing the distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), plus roi_proof metrics showing raw token count, distilled token count, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and ROI multiplier. Also includes cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns an error status","Token budget too low (max_tokens < 20) causes validation failure","BM25 query provided without mode=budget may be ignored","Raw HTML too large may cause timeout or truncation","Payment required (HTTP 402) if x402 credentials are missing or invalid","builtin:// scheme only valid for whitelisted built-in document sets"],"whenToPreferThis":"Choose this endpoint when you need to feed web content to an LLM but want to minimize token consumption and cost — particularly when you have a specific query focus (BM25 mode) or a hard token budget ceiling. Prefer over raw web scraping when you need clean markdown or structured output ready for agent consumption. Especially useful in agentic pipelines where context window size is a binding constraint.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:39.341Z","isFirstParty":false,"canonicalSlug":"token-intel-agentdiet-dev-web-url-context-trimmer-bm25-budget-5b1f719f"}