{"uid":"cap_78DO-eFciCvo5-4tEi66E","slug":"preflight-agentdiet-dev-web-url-context-trimmer-with-bm25-budget-55120452","name":"Web URL Context Trimmer 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://preflight.agentdiet.dev/v1/context-trimmer)","url":"https://preflight.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_5eFWAOQLjgLaBKWIjksKZ","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"preflight.agentdiet.dev","brandSlug":"preflight-agentdiet-dev-mpp","brandBaseUrl":"https://preflight.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or raw HTML and distills it into compact, agent-ready tokens using configurable modes (markdown, structured, skeleton, or BM25 budget) with a strict token ceiling","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments into compact markdown, keeping it under 2000 tokens using budget mode focused on 'payment intents'?","exampleUseCases":[{"title":"Compress docs page for in-context retrieval","prompt":"Fetch https://docs.openai.com/api-reference and distill it into structured markdown so I can include the key info in my prompt without blowing my context window."},{"title":"BM25 budget excerpt for targeted research","prompt":"Pull https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) and give me a BM25 budget excerpt focused on 'attention mechanism', capped at 500 tokens."},{"title":"Skeleton outline of a long article","prompt":"Distill https://www.paulgraham.com/greatwork.html in skeleton mode so I just get the high-level structure and section headings without all the body text."}],"resultDescription":"Returns a 'data' object containing the distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, ROI multiplier, and estimated LLM cost saved in USD. Also includes optional billing details and a cache hit/miss indicator with latency.","failureModes":["URL unreachable or returns non-200 — endpoint may return an error status","HTML too large or malformed — distillation may fail or return partial content","max_tokens too low (below 20) — rejected by schema validation","BM25 query missing when mode=budget — may fall back to default or return error","Payment not completed via x402 — 402 response blocking access","Invalid mode enum value — request rejected"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read web content but must stay within a token budget or minimize LLM costs. It is especially useful when passing full web pages to an LLM is impractical due to context window limits. Prefer it over generic scrapers when you need structured output modes (markdown, skeleton, structured tables) or BM25-focused excerpts. The built-in ROI proof makes it easy to justify the compression step in agent pipelines. Use it over browser automation tools when raw content retrieval and compression are sufficient — no JavaScript rendering required.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:26:33.854Z","isFirstParty":false,"canonicalSlug":"preflight-agentdiet-dev-web-url-context-trimmer-with-bm25-budget-55120452"}