{"uid":"cap_opoZlJ3T2qyJ4Von_8FRj","slug":"llms-generator-agentdiet-dev-webpage-distiller-compact-agent-ready-72d157b6","name":"Webpage Distiller – Compact Agent-Ready Token Extractor","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/webpage-distiller)","url":"https://llms-generator.agentdiet.dev/v1/webpage-distiller?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_QakaFAFJQfK1i_EfpNKkg","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 URL or raw HTML and distills it into compact, agent-ready content using markdown, structured, skeleton, or BM25 budget modes with strict token ceiling control.","exampleAgentPrompt":"Distill this URL for me — https://stripe.com/docs/payments — using budget mode with a focus query on 'payment intents' and cap it at 500 tokens so I don't blow my context window.","exampleUseCases":[{"title":"Condense documentation for agent context","prompt":"Grab the Stripe docs at https://stripe.com/docs/api and distill them into markdown under 800 tokens so my agent can reason about the API without filling up the whole context window."},{"title":"Structured data extraction from a product page","prompt":"Fetch https://example.com/product/widget-pro and give me a structured JSON output of all tables and metadata on that page — I need pricing and specs in a clean format."},{"title":"BM25 topic-focused page excerpt","prompt":"Distill https://en.wikipedia.org/wiki/Retrieval-augmented_generation using budget mode, focus query 'vector databases', and limit it to 300 tokens — just the most relevant chunk."}],"resultDescription":"Returns a 'data' object containing the distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt), alongside an 'roi_proof' object showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved in USD. Also includes optional cache hit/miss info and billing metadata.","failureModes":["Invalid or unreachable URL returns an error status","Missing required 'url' parameter causes a 400-level error","mode=budget without a query or max_tokens may return unfiltered content","Paywalled or bot-blocked pages may return empty or partial content","Very large pages may exceed internal fetch limits","Payment failure (x402) blocks the call if no valid payment header is supplied"],"whenToPreferThis":"Choose this endpoint when your agent needs to read and reason about web pages without exhausting its context window — especially when token budget is a concern. It is superior to raw HTML scraping when you need clean, agent-ready output. Prefer budget mode with a BM25 query when you only need content relevant to a specific topic. Use structured mode when you need tabular or metadata output rather than prose.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:24:26.808Z","isFirstParty":false,"canonicalSlug":"llms-generator-agentdiet-dev-webpage-distiller-compact-agent-ready-72d157b6"}