{"uid":"cap_1nfnSu8l8H64aa0K_xnNG","slug":"workflows-agentdiet-dev-web-url-distillation-bm25-token-budget-api-03d5fff4","name":"Web URL Distillation & BM25 Token Budget API","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://workflows.agentdiet.dev/v1/web-scrape)","url":"https://workflows.agentdiet.dev/v1/web-scrape?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__IicX58jZTryNM7EUIiy9","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"workflows.agentdiet.dev","brandSlug":"workflows-agentdiet-dev-mpp","brandBaseUrl":"https://workflows.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills any web URL (or raw HTML) into compact, agent-ready tokens using markdown, structured, skeleton, or BM25-budget extraction modes","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it into markdown, keeping it under 800 tokens using BM25 budget mode focused on 'payment intents'.","exampleUseCases":[{"title":"Competitive pricing page extraction","prompt":"Grab https://www.notion.so/pricing and pull out the structured pricing tiers and plan details — keep it tight, under 600 tokens, using budget mode focused on 'plan pricing features'."},{"title":"Research article skeleton for agent pipeline","prompt":"Fetch https://arxiv.org/abs/2310.06825 and give me a skeleton outline of the paper so I can quickly understand its structure without blowing my token budget."},{"title":"Shopify product page as structured JSON","prompt":"Distill https://allbirds.com/products/mens-wool-runners into structured mode so I can extract the product name, price, variants, and description as clean JSON."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (markdown text, structured tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), plus an roi_proof object showing raw vs distilled token counts, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Also includes cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 — status error returned","URL points to a PDF or binary file not parseable as HTML — may return empty or partial data","max_tokens set too low (below 20) — validation error","mode=budget used without a query parameter — BM25 focus may be undefined","Payment not attached or insufficient — HTTP 402 returned before processing","Rate limiting or timeout on slow remote URLs — partial or error response"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web content but must minimize token consumption and LLM costs. It is especially valuable when you have a strict token budget (use budget mode + max_tokens), want structured or outline extraction rather than raw HTML, or need BM25-ranked relevance filtering against a specific query. Prefer this over generic scraping tools when token ROI measurement and compression ratio reporting matter to your pipeline.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:50.536Z","isFirstParty":false,"canonicalSlug":"workflows-agentdiet-dev-web-url-distillation-bm25-token-budget-api-03d5fff4"}