{"uid":"cap_mMYyZuNkU2f0OVmJv3Lpn","slug":"prompt-guard-agentdiet-dev-web-url-context-trimmer-distiller-a84d079f","name":"Web URL Context Trimmer & Distiller","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://prompt-guard.agentdiet.dev/v1/context-trimmer)","url":"https://prompt-guard.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_SJUzWUGTAV1uVkLthnUJe","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"prompt-guard.agentdiet.dev","brandSlug":"prompt-guard-agentdiet-dev-mpp","brandBaseUrl":"https://prompt-guard.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or raw HTML and distills it into compact, agent-ready tokens using BM25 budget control and multiple extraction modes.","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments into compact markdown — keep it under 1500 tokens and focus on anything related to payment intents?","exampleUseCases":[{"title":"Trim docs page for LLM context","prompt":"Distill https://docs.openai.com/api-reference/chat into structured markdown for me — I only have about 800 tokens of context budget and want to focus on the 'messages' parameter."},{"title":"Extract structured tables from a landing page","prompt":"Pull the pricing page at https://vercel.com/pricing and give it to me in structured mode so I can compare the plan tiers in a clean table format."},{"title":"Skeleton outline of a long article","prompt":"Get a skeleton outline of https://en.wikipedia.org/wiki/Large_language_model — I just need the section headers and key sub-topics, not the full content."}],"resultDescription":"Returns a 'data' object containing the distilled content in the requested mode (Markdown, structured JSON, skeleton outline, or BM25-ranked excerpt), plus an 'roi_proof' object showing raw vs distilled token counts, tokens saved, compression ratio, and estimated LLM cost savings, and optionally cache status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","mode=budget without a query or max_tokens may produce unfiltered output","Very large HTML pages may exceed processing limits","Rate limiting or payment failures via x402 may block the request","Paywalled or JavaScript-rendered pages may return incomplete content"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read web content but must stay within a strict token budget, or when raw HTML is too verbose to include in a prompt. It is especially valuable over generic scrapers when BM25 query-focused trimming is needed, when structured/skeleton extraction modes are required, or when token-cost ROI metrics are important for agent cost management.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:47.937Z","isFirstParty":false,"canonicalSlug":"prompt-guard-agentdiet-dev-web-url-context-trimmer-distiller-a84d079f"}