{"uid":"cap_aQQ-Zyf8sALZqT54fpoq5","slug":"arxiv-digest-agentdiet-dev-web-url-prompt-compressor-with-bm25-budget-3baa2bcd","name":"Web URL Prompt Compressor 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://arxiv-digest.agentdiet.dev/v1/prompt-compress)","url":"https://arxiv-digest.agentdiet.dev/v1/prompt-compress?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_ys6O-Rc6JpVsnHixv2bP9","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 and distills a webpage URL or raw HTML into compact, agent-ready tokens using configurable extraction modes and BM25-based token budget control.","exampleAgentPrompt":"Grab https://docs.stripe.com/payments and distill it into structured mode with a 500-token budget — I need a compact, agent-ready version I can fit inside my LLM context without burning tokens.","exampleUseCases":[{"title":"Compress docs page for LLM context","prompt":"Fetch https://docs.openai.com/api-reference and compress it into markdown mode so I can paste the result into my agent's context window without hitting token limits."},{"title":"BM25 budget excerpt for research query","prompt":"Distill https://arxiv.org/abs/2305.10601 using budget mode with the query 'attention mechanism efficiency' and a max of 300 tokens — I only need the parts most relevant to that topic."},{"title":"Skeleton outline of a competitor page","prompt":"Give me a skeleton outline of https://www.anthropic.com/research so I can see the structure and headings without reading the whole page."}],"resultDescription":"Returns a data object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-filtered excerpt depending on mode), along with an roi_proof block showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Also includes cache status and billing details.","failureModes":["URL is unreachable or returns non-200 — fetch failure error","Invalid or missing URL parameter — 400 validation error","max_tokens below minimum of 20 when mode=budget — schema validation error","mode=budget requested without a query parameter — incomplete BM25 context","Raw HTML too large to process within token constraints — truncation or error","Payment/x402 authentication failure — 402 payment required","Timeout fetching slow or large target URLs"],"whenToPreferThis":"Choose this endpoint when you need to reduce the token footprint of web content before passing it to an LLM — especially when working with long documentation pages, research papers, or any URL where full content exceeds your context budget. Prefer it over generic web scrapers when you need BM25-focused relevance filtering (mode=budget), structured JSON table extraction (mode=structured), or skeleton outlines (mode=skeleton) rather than raw HTML. It is particularly well-suited for autonomous agents that need to stay within strict token budgets while still grounding responses in live web content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:43:18.247Z","isFirstParty":false,"canonicalSlug":"arxiv-digest-agentdiet-dev-web-url-prompt-compressor-with-bm25-budget-3baa2bcd"}