{"uid":"cap_2YgLTiL6ga1iY5NK4C3Dr","slug":"token-intel-agentdiet-dev-web-content-distiller-with-bm25-budget-37ceec4b","name":"Web Content Distiller 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-trimmer)","url":"https://token-intel.agentdiet.dev/v1/context-trimmer?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_BdpKcBqyb3RN9Z68uaUfH","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 URL or accepts raw HTML and distills it into compressed markdown, structured data, skeleton outline, or a BM25-ranked token-budget excerpt","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it in budget mode focused on the query 'payment intents API' with a max of 1500 tokens, so I can pass just the relevant section into my prompt.","exampleUseCases":[{"title":"Researching a competitor's pricing page","prompt":"Grab https://linear.app/pricing and distill it into clean markdown so I can read through their plan features without all the HTML clutter."},{"title":"Staying under token budget for RAG pipeline","prompt":"I need to pull content from https://docs.anthropic.com/claude/reference/getting-started-with-the-api but keep it under 800 tokens — use budget mode and focus the BM25 query on 'streaming responses'."},{"title":"Extracting structured data from a news article","prompt":"Take this raw HTML I've pasted and distill it into structured mode so I get the tables and metadata pulled out cleanly as JSON."}],"resultDescription":"Returns a distilled representation of the webpage or HTML in the chosen mode (markdown, structured JSON, skeleton outline, or BM25 budget excerpt), along with ROI proof metrics showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved in USD. Also includes cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 — fetch failure with error status","max_tokens set below 20 — validation error","mode=budget used without a query field — may return unranked or degraded output","Raw HTML too large to process within limits — truncation or timeout","Payment not completed — HTTP 402 returned, endpoint requires x402 payment","Invalid URL format — schema validation error"],"whenToPreferThis":"Choose this endpoint when you need to inject web content into an LLM prompt but must control token spend — especially in RAG pipelines, agent research loops, or summarization chains. The BM25 budget mode is uniquely suited for pulling only the most topically relevant passages from long documents when you have a specific query. Prefer this over generic scraping tools when token efficiency and LLM cost reduction are priorities.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:32:21.426Z","isFirstParty":false,"canonicalSlug":"token-intel-agentdiet-dev-web-content-distiller-with-bm25-budget-37ceec4b"}