{"uid":"cap_SSkT7opTax0WasOCaaNNt","slug":"domain-osint-agentdiet-dev-web-url-prompt-compressor-with-bm25-budget-14414ad3","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://domain-osint.agentdiet.dev/v1/prompt-compress)","url":"https://domain-osint.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_Xw6T5HuGSCZLZ9xFKoHRv","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"domain-osint.agentdiet.dev","brandSlug":"domain-osint-agentdiet-dev-mpp","brandBaseUrl":"https://domain-osint.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a webpage or raw HTML and distills it into compact, agent-ready tokens using configurable modes (markdown, structured, skeleton, or BM25 budget-focused excerpts)","exampleAgentPrompt":"Distill https://stripe.com/docs/payments/intents into compact markdown using budget mode, focused on 'payment intents lifecycle', and cap it at 500 tokens.","exampleUseCases":[{"title":"Token-efficient doc ingestion for agents","prompt":"Grab the content from https://docs.openai.com/api-reference and compress it into markdown mode so I can fit it into my agent's context window without blowing my token budget."},{"title":"BM25 focused excerpt for research","prompt":"I need just the parts of https://en.wikipedia.org/wiki/Retrieval-augmented_generation relevant to 'chunking strategies' — use budget mode with a max of 300 tokens so my LLM only sees what matters."},{"title":"Structured data extraction from a webpage","prompt":"Pull https://news.ycombinator.com and distill it in structured mode so I get a clean JSON table of the posts, scores, and links without all the HTML noise."}],"resultDescription":"Returns a data object containing the distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt), plus an roi_proof object showing raw vs distilled token counts, compression ratio percentage, tokens saved, and estimated LLM cost saved in USD. Also includes cache status and billing details.","failureModes":["URL unreachable or returns non-200 status — endpoint may return error status","Invalid or malformed URL — validation error on url parameter","max_tokens too small (below 20) — rejected by schema validation","mode=budget used without a query parameter — may produce unguided output","Rate limiting or payment failure via x402 — HTTP 402 returned if payment not processed","HTML too large to process within time limits — potential timeout"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web content but must stay within a strict token budget or reduce LLM inference costs. It is especially useful when you have a specific focus query (BM25 budget mode) and want only the most relevant passage from a long webpage, or when you need structured/skeleton extraction rather than raw HTML. Prefer it over generic scraping tools when token efficiency and cost savings are the primary concern.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:22:53.079Z","isFirstParty":false,"canonicalSlug":"domain-osint-agentdiet-dev-web-url-prompt-compressor-with-bm25-budget-14414ad3"}