{"uid":"cap_iW7cPy1_y93kfJTO0-VNR","slug":"x402broker-com-web-url-distillation-with-bm25-budget-control-2d199006","name":"Web URL Distillation 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://x402broker.com/api/diet)","url":"https://x402broker.com/api/diet?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__NtunLb8-3OVtFA6egjvQ","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"x402broker.com","brandSlug":"x402broker-com-mpp","brandBaseUrl":"https://x402broker.com","brandDocsUrl":null,"whatItDoes":"Fetches and compresses a web URL or raw HTML into compact, agent-ready tokens using configurable distillation modes including BM25 budget-constrained excerpts","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/api and distill it into compact markdown using budget mode with the query 'payment intents' and a max of 500 tokens?","exampleUseCases":[{"title":"LLM cost reduction for research agents","prompt":"Distill https://openai.com/research/gpt-4 into budget mode focused on the query 'model capabilities' with a max of 300 tokens so I can feed just the relevant bits to my LLM without blowing the context window."},{"title":"Structured data extraction from docs page","prompt":"Fetch https://docs.stripe.com/api/charges and convert it into structured mode so I get the tables and metadata in JSON format — I want to understand all the charge object fields."},{"title":"Quick skeleton outline of a long article","prompt":"Grab https://en.wikipedia.org/wiki/Large_language_model and give me a skeleton outline so I can see the section headings and structure without reading the whole page."}],"resultDescription":"Returns a distilled representation of the target URL or HTML in the chosen mode (markdown, structured JSON, skeleton outline, or BM25 budget excerpt), along with ROI proof metrics including raw token count, distilled token count, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and optional cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","HTML fetch timeout for slow or blocked websites","max_tokens below minimum of 20 is rejected","BM25 query provided without mode=budget may be ignored","Rate limiting or payment failure due to x402 payment protocol issues","malformed raw HTML input may produce poor distillation quality"],"whenToPreferThis":"Choose this endpoint when you need to feed web page content to an LLM but want to minimize token usage and cost — especially when working with long documentation pages, news articles, or reference sites. It is ideal when you have a specific focus query (BM25 budget mode) and need only the most relevant content under a strict token ceiling. Prefer it over raw HTML fetching when compression ratio and ROI tracking matter, or when you need structured JSON tables or a skeleton outline instead of full prose.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:42:45.512Z","isFirstParty":false,"canonicalSlug":"x402broker-com-web-url-distillation-with-bm25-budget-control-2d199006"}