{"uid":"cap_ltPBko3L4LRRAV4NHSdz2","slug":"llms-generator-agentdiet-dev-web-url-distillation-bm25-token-6090b671","name":"Web URL Distillation & BM25 Token Compression API","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://llms-generator.agentdiet.dev/v1/pdf-extract)","url":"https://llms-generator.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_NbHvnV19dgICajavBTXDF","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"llms-generator.agentdiet.dev","brandSlug":"llms-generator-agentdiet-dev-mpp","brandBaseUrl":"https://llms-generator.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a webpage or raw HTML and distills it into compact, agent-ready markdown, structured data, skeleton outline, or BM25-focused excerpts with token budget control","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it into markdown mode, keeping it under 2000 tokens so I can read the key content without blowing my context window.","exampleUseCases":[{"title":"Summarize documentation page for agent","prompt":"Grab https://docs.openai.com/api-reference and distill it into structured mode so I can quickly see the tables and metadata without reading the whole thing."},{"title":"Budget-focused research with BM25 query","prompt":"Distill https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) in budget mode, focusing on the query 'attention mechanism', and keep it under 500 tokens."},{"title":"Convert competitor page to clean markdown","prompt":"Fetch https://www.anthropic.com/product and give me the content as clean markdown — I want to read through it without all the HTML noise."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (markdown text, structured tables/metadata, skeleton outline, or BM25 excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes optional billing and cache metadata.","failureModes":["Invalid or unreachable URL returns an error status","URL behind authentication/paywalls cannot be fetched","max_tokens too low may truncate content excessively","mode=budget without a query may produce suboptimal BM25 results","Raw HTML too large may time out or exceed processing limits","Payment failure via x402 prevents execution"],"whenToPreferThis":"Choose this endpoint when you need to reduce token consumption while reading web content inside an AI agent context — especially when a raw page would overflow your context window. It is particularly valuable in agentic workflows where LLM costs matter and you want BM25-focused excerpts or structured extraction rather than raw HTML. Prefer it over generic scrapers when you need ROI-proven token compression with budget control.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:20:59.001Z","isFirstParty":false,"canonicalSlug":"llms-generator-agentdiet-dev-web-url-distillation-bm25-token-6090b671"}