{"uid":"cap_UDbxIRW7QoqObTn74HTW2","slug":"whale-momentum-agentdiet-dev-web-distillation-with-bm25-budget-control-2de098c3","name":"Web 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://whale-momentum.agentdiet.dev/v1/web-scrape)","url":"https://whale-momentum.agentdiet.dev/v1/web-scrape?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_S_4IA0AfFrVJBq4gGbRkg","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 Markdown, structured JSON, skeleton, or BM25-focused excerpt with token budget enforcement","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/api and distill it into markdown, keeping only the parts relevant to 'webhook event handling' and staying under 2000 tokens?","exampleUseCases":[{"title":"Stripe docs research for agent","prompt":"Grab the Stripe docs page at https://stripe.com/docs/payments and distill it in budget mode focused on 'payment intent lifecycle', keeping it under 1500 tokens so I don't blow my context window."},{"title":"Competitor pricing page extraction","prompt":"Scrape https://www.competitor.com/pricing and give me a structured JSON breakdown of their pricing tiers and features — I want to compare them to ours."},{"title":"Compress raw HTML for analysis","prompt":"I have this raw HTML from a news article — can you distill it down to just the main article content as clean markdown so I can feed it to another model without wasting tokens?"}],"resultDescription":"Returns a distilled representation of the webpage or HTML in the chosen mode (Markdown, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt), along with ROI proof metrics including raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost savings. Also includes cache status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","max_tokens set below minimum of 20 is rejected","mode=budget without a query may produce unfocused results","Rate limiting or paywalled pages may return incomplete content","Malformed raw HTML may produce poor distillation quality","Payment failure (x402) if USDC balance is insufficient"],"whenToPreferThis":"Choose this endpoint when you need to fetch and compress web content to fit within LLM context windows, especially when token cost is a concern. The BM25 budget mode is uniquely suited for agents that need only query-relevant snippets from large pages. Prefer this over generic scrapers when you need ROI proof of token savings or when working with large documentation sites like Stripe docs. The $0.001/call pricing makes it cost-effective for high-volume agent workflows.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:32:30.222Z","isFirstParty":false,"canonicalSlug":"whale-momentum-agentdiet-dev-web-distillation-with-bm25-budget-control-847a3290"}