{"uid":"cap_X9q3VPUEy1ncsow4cQtes","slug":"token-intel-agentdiet-dev-web-url-distiller-token-compressor-f29ad9e6","name":"Web URL Distiller & Token Compressor","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":"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_Asfz7UYDlrDNIB7_qvtho","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 a webpage or raw HTML and distills it into compact, agent-ready tokens using BM25 budget control and multiple extraction modes","exampleAgentPrompt":"Can you fetch the Stripe docs page at https://stripe.com/docs/payments and distill it into clean markdown, keeping it under 1000 tokens and focusing on the 'payment intents' topic?","exampleUseCases":[{"title":"LLM cost-efficient research scraping","prompt":"Pull the content from https://techcrunch.com/2024/05/01/openai-news/ and compress it into budget mode with a max of 500 tokens, focusing my query on 'funding round' — I want to keep my LLM costs down."},{"title":"Structured data extraction from product page","prompt":"Scrape https://www.amazon.com/dp/B0EXAMPLE and give me the result in structured mode so I can pull out the product tables and metadata cleanly."},{"title":"Page skeleton for agent navigation","prompt":"Give me a skeleton outline of https://docs.anthropic.com/claude/reference/getting-started so my agent can quickly understand the page structure before deciding which section to dive into."}],"resultDescription":"Returns a data object containing distilled content in the requested mode (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-filtered excerpt), along with an roi_proof object showing raw vs. distilled token counts, tokens saved, compression ratio percentage, LLM cost saved in USD, and ROI multiplier. Also includes cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns an error status","URL behind authentication or paywalls may return incomplete or empty content","max_tokens too low (below 20) triggers validation error","BM25 query with mode other than budget may be ignored","Raw HTML too large may exceed processing limits","Payment failure via x402 returns HTTP 402"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to process webpage content but wants to minimize LLM token consumption and cost. It is especially valuable when you need BM25-focused topic filtering to retrieve only the most relevant portions of a page, when you want structured table extraction rather than raw HTML, or when you need a skeleton outline for navigation planning. Prefer this over generic scraping tools when token efficiency and LLM cost savings are priorities.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:28.007Z","isFirstParty":false,"canonicalSlug":"token-intel-agentdiet-dev-web-url-distiller-token-compressor-f29ad9e6"}