{"uid":"cap_GwhhEgGfrcYjFHgMIgrYt","slug":"whale-momentum-agentdiet-dev-webpage-distiller-with-bm25-budget-control-1de00897","name":"Webpage Distiller 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://whale-momentum.agentdiet.dev/v1/webpage-distiller)","url":"https://whale-momentum.agentdiet.dev/v1/webpage-distiller?utm_source=zero.xyz","method":"POST","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_NmF6nGncPzJSYM5Z5s0tt","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"whale-momentum.agentdiet.dev","brandSlug":"whale-momentum-agentdiet-dev-mpp","brandBaseUrl":"https://whale-momentum.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into compressed Markdown, structured JSON, a skeleton outline, or a BM25-ranked token-budgeted excerpt","exampleAgentPrompt":"Distill the content at https://openai.com/research/gpt-4 into clean markdown using BM25 budget mode, focusing on 'model capabilities and benchmarks', and keep it under 500 tokens.","exampleUseCases":[{"title":"LLM context-efficient webpage summarization","prompt":"Fetch https://stripe.com/docs/payments/accept-a-payment and distill it into clean markdown — I need to feed it to an LLM without blowing my token budget."},{"title":"BM25 focused excerpt for research","prompt":"Pull the content from https://arxiv.org/abs/2305.10403 and use budget mode with the query 'chain-of-thought reasoning performance' to give me only the most relevant 300 tokens."},{"title":"Structured data extraction from product page","prompt":"Distill https://www.apple.com/iphone-15-pro/ in structured mode so I get the product specs, pricing tiers, and metadata as JSON tables."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown, structured JSON, skeleton, or BM25 excerpt depending on mode), an ROI proof object showing raw vs distilled token counts, compression ratio, and estimated LLM cost savings, plus optional billing and cache metadata.","failureModes":["Invalid or unreachable URL returns a fetch error","HTML too large to process within budget may return truncated output","mode='budget' without a 'query' parameter may return unranked content","max_tokens set too low (< 20) is rejected by schema validation","Paywalled or JS-rendered pages may return incomplete distillation","Payment failure via x402 returns HTTP 402 with payment details"],"whenToPreferThis":"Choose this endpoint when you need to feed web content to an LLM and want to minimize token consumption — especially in budget mode with BM25 query ranking to extract only the most relevant content. Prefer it over raw fetch+parse pipelines when you need built-in compression metrics, ROI proof, and token ceiling enforcement. It is particularly valuable for agents that need to process many pages cheaply or need to stay within context window limits.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:33:38.333Z","isFirstParty":false,"canonicalSlug":"whale-momentum-agentdiet-dev-webpage-distiller-with-bm25-budget-control-1de00897"}