{"uid":"cap_51D7L7SDmwu2IQ3d_H8SO","slug":"token-intel-agentdiet-dev-web-distill-with-bm25-budget-control-7a8a051d","name":"Web Distill 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://token-intel.agentdiet.dev/v1/web-scrape)","url":"https://token-intel.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_P5DC3EGV4mp9g2gE1etRY","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"token-intel.agentdiet.dev","brandSlug":"token-intel-agentdiet-dev-mpp","brandBaseUrl":"https://token-intel.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into compressed Markdown, structured JSON, skeleton outline, or BM25-focused excerpt with token budget control","exampleAgentPrompt":"Fetch the page at https://stripe.com/docs/api and distill it into a BM25 budget excerpt focused on 'payment intents' keeping it under 500 tokens so I can feed it to my LLM without blowing the context window.","exampleUseCases":[{"title":"Token-budget research from live docs","prompt":"Grab the page at https://docs.openai.com/api-reference and give me a BM25 excerpt focused on 'function calling' with a max of 800 tokens — I need to fit it into my agent's context window cheaply."},{"title":"Convert competitor pricing page to structured data","prompt":"Fetch https://linear.app/pricing and distill it into structured JSON tables so I can compare their pricing tiers programmatically."},{"title":"Skeleton outline of a long article","prompt":"I have this raw HTML from a TechCrunch article — can you distill it into a skeleton outline so I can quickly scan the section headings without reading the whole thing?"}],"resultDescription":"Returns a distilled payload in the requested mode (Markdown, structured JSON, skeleton outline, or BM25 excerpt), along with an ROI proof object showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved. Also includes cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns a fetch error","Missing required 'url' field returns a 400 validation error","max_tokens set below 20 returns a validation error","BM25 query provided without mode=budget may be ignored","Rate limiting or payment failure (x402) blocks execution","HTML-only input without url field requires 'html' field to be populated"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM but want to minimize token usage and cost — especially when using mode=budget with a BM25 query to extract only the most relevant passage from a large page. Prefer over generic scrapers when token compression and ROI metrics matter, or when you need structured JSON tables or skeleton outlines rather than raw HTML dumps.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:37:44.390Z","isFirstParty":false,"canonicalSlug":"token-intel-agentdiet-dev-web-distill-with-bm25-budget-control-7a8a051d"}