{"uid":"cap_B38mOzoU-61YCf7KVJdSw","slug":"cve-intel-agentdiet-dev-web-url-html-distillation-with-bm25-budget-14b696aa","name":"Web URL & HTML 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://cve-intel.agentdiet.dev/v1/pdf-extract)","url":"https://cve-intel.agentdiet.dev/v1/pdf-extract?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_vqbo5jBk_HGRc1ZliRUKn","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"cve-intel.agentdiet.dev","brandSlug":"cve-intel-agentdiet-dev-mpp","brandBaseUrl":"https://cve-intel.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a webpage URL or raw HTML and distills it into compact, agent-ready tokens using configurable modes including markdown, structured, skeleton, or BM25-focused budget excerpts.","exampleAgentPrompt":"Distill https://stripe.com/docs/api into compact markdown using budget mode with a focus query on 'payment intents' and a max of 500 tokens so I can feed it to my LLM without blowing my context window.","exampleUseCases":[{"title":"Token-efficient doc ingestion for LLM pipeline","prompt":"Fetch https://docs.openai.com/api-reference and distill it into structured mode so I can pass it to my agent without eating up my context budget."},{"title":"BM25-focused excerpt from a long article","prompt":"Grab https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) and give me a budget-mode excerpt focused on 'attention mechanism' with a max of 300 tokens."},{"title":"Convert raw HTML to clean markdown","prompt":"I have a raw HTML blob from a scraped product page — distill it into clean markdown so my agent can read the key details without the noise."}],"resultDescription":"Returns a JSON object containing the distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), along with ROI proof metrics including raw vs distilled token counts, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and optional billing and cache status fields.","failureModes":["URL is unreachable or returns non-200 HTTP status — endpoint may return an error status","HTML payload too large to process within service limits","Invalid or missing 'url' parameter causes 400-level error","mode=budget without a 'query' parameter may produce suboptimal excerpts","Payment failure via x402 protocol blocks request execution","Token budget ceiling too low (below minimum 20) causes validation error"],"whenToPreferThis":"Choose this endpoint when you need to feed web content to an LLM but want to minimize token consumption and cost — especially when working with long documentation pages, article archives, or HTML payloads where only the relevant sections matter. The BM25 budget mode is particularly powerful when you have a specific focus query and a hard token ceiling. Prefer this over raw web scraping when you need agent-ready, pre-compressed output rather than raw HTML.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:51:32.590Z","isFirstParty":false,"canonicalSlug":"cve-intel-agentdiet-dev-web-url-html-distillation-with-bm25-budget-14b696aa"}