{"uid":"cap_Wi12Oml7IKCox6VfDFj1M","slug":"whale-momentum-agentdiet-dev-web-url-distiller-with-bm25-budget-control-bb9b72a5","name":"Web URL 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/pdf-extract)","url":"https://whale-momentum.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_SVYc6XgoTYjlJlW9e-__l","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 compresses a web URL or raw HTML into compact, agent-ready tokens using configurable distillation modes and BM25 budget control","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it into compact markdown using budget mode with the query 'payment intents' and a max of 500 tokens, so I can read it without burning through my context window.","exampleUseCases":[{"title":"Stripe docs lookup for agent","prompt":"Grab the Stripe API docs from builtin://stripe-docs and distill them into structured mode so I can find the table of endpoints and pricing without reading the whole thing."},{"title":"Summarize competitor landing page","prompt":"Fetch https://www.anthropic.com/index and distill it into skeleton mode so I get just the outline of what's on the page — headings and key sections only."},{"title":"Budget-capped news article extraction","prompt":"Distill https://techcrunch.com/latest into budget mode with the query 'AI funding rounds' and cap it at 300 tokens so I only get the parts relevant to recent AI investments."}],"resultDescription":"Returns a distilled representation of the webpage in the chosen mode (markdown, structured JSON tables, skeleton outline, or BM25-focused excerpt), plus ROI proof metrics showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost savings. Also includes cache status and billing details.","failureModes":["URL is unreachable or returns non-200 — endpoint may error or return empty data","HTML payload too large to process within budget constraints","BM25 query yields no relevant matches — returns minimal or empty excerpt","Invalid mode enum value — request rejected","max_tokens below minimum of 20 — validation error","Payment failure via x402 — request blocked"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read web content but must stay within a token budget, or when raw HTML is too noisy and verbose for direct LLM consumption. Ideal when you need BM25-focused extraction to surface only query-relevant passages, or when you want structured/skeleton modes to navigate large documentation pages efficiently. Prefer over generic scrapers when token cost savings and compression metrics matter to your workflow.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:43:54.051Z","isFirstParty":false,"canonicalSlug":"whale-momentum-agentdiet-dev-web-url-distiller-with-bm25-budget-control-0d63b48b"}