{"uid":"cap_xWqXCFdv9PXnRYXRJkswg","slug":"arxiv-digest-agentdiet-dev-web-url-context-trimmer-distiller-caae71f6","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://arxiv-digest.agentdiet.dev/v1/context-trimmer)","url":"https://arxiv-digest.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_wYVyrBaZ-8mB9iSCu87E9","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"arxiv-digest.agentdiet.dev","brandSlug":"arxiv-digest-agentdiet-dev-mpp","brandBaseUrl":"https://arxiv-digest.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a webpage or raw HTML and distills it into compact, agent-ready tokens using BM25 budget control and multiple extraction modes","exampleAgentPrompt":"Distill https://docs.stripe.com/payments/payment-intents into compact markdown using budget mode, focusing on 'authentication flow' and keeping it under 500 tokens.","exampleUseCases":[{"title":"Trim research paper for agent context","prompt":"Can you distill https://arxiv.org/abs/2310.06825 into structured markdown so I can fit it in my context window without wasting tokens?"},{"title":"BM25 focused extraction from docs page","prompt":"Fetch https://docs.openai.com/api-reference and extract only the parts relevant to 'rate limits' using budget mode, max 300 tokens."},{"title":"Convert raw HTML to clean skeleton","prompt":"I have raw HTML from a product page — can you distill it into a skeleton outline so I can quickly understand its structure without all the boilerplate?"}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown, structured JSON, skeleton, or BM25-budgeted excerpt), plus an 'roi_proof' block showing raw vs. distilled token counts, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and ROI multiplier. Also includes optional cache status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","Token budget too small (max_tokens below 20) causes validation failure","HTML payload too large may exceed processing limits","mode=budget without a query param may return unfiltered or generic results","Paywalled or bot-blocked pages may return empty or partial content","Network timeouts on slow or unresponsive URLs"],"whenToPreferThis":"Choose this endpoint when you need to feed webpage content into an LLM but want to minimize token usage and cost. It is especially valuable when you have a specific query focus (use mode=budget with a BM25 query) or need structured/skeleton output rather than raw HTML. Prefer this over raw fetch-and-pass approaches when token budget matters, or when you need ROI proof of compression savings. It supports both URL fetching and direct HTML input, making it flexible for both live and cached content pipelines.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:48.755Z","isFirstParty":false,"canonicalSlug":"arxiv-digest-agentdiet-dev-web-url-context-trimmer-distiller-caae71f6"}