{"uid":"cap_g2PZDaQe83Cb21JMnIYP9","slug":"mesh-agentdiet-dev-web-url-html-distillation-to-compact-agent-ready-67db2e29","name":"Web URL & HTML Distillation to Compact Agent-Ready Tokens","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://mesh.agentdiet.dev/v1/pdf-extract)","url":"https://mesh.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_Ojkfg2qXKSCQ1Abz9tMD1","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"mesh.agentdiet.dev","brandSlug":"mesh-agentdiet-dev-mpp","brandBaseUrl":"https://mesh.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or raw HTML and compresses it into token-efficient markdown, structured JSON, outline skeleton, or BM25-focused excerpts with token budget control","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it into compact markdown, keeping it under 1500 tokens — I only care about sections related to payment intents.","exampleUseCases":[{"title":"Token-budget documentation ingestion","prompt":"Pull https://docs.openai.com/api-reference/chat and distill it in budget mode with the query 'streaming responses', keeping the output under 800 tokens so it fits in my prompt."},{"title":"Structured data extraction from landing page","prompt":"Grab https://linear.app and distill it in structured mode — I want pricing tiers, feature lists, and any metadata extracted as JSON tables."},{"title":"Raw HTML compression for agent pipeline","prompt":"I have raw HTML from a scraped product page — distill it into clean markdown so my agent can read just the key content without wasting tokens on nav bars and footers."}],"resultDescription":"Returns a JSON object containing distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), an roi_proof block showing raw vs distilled token counts, compression ratio percentage, tokens saved, and estimated LLM cost saved in USD, plus optional cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns an error status","URL blocked by robots.txt or firewall returns empty or error","Exceeding max_tokens with very short content may yield minimal output","BM25 budget mode with no query match returns low-relevance excerpts","Raw HTML input too large may be truncated","Payment/402 failure if USDC balance insufficient"],"whenToPreferThis":"Choose this endpoint when your agent needs to read or summarize web pages while staying within LLM token budgets — especially useful in RAG pipelines, documentation ingestion, competitive research, or any workflow where raw HTML would blow up context windows. Prefer it over generic scrapers when you need token-count guarantees (budget mode) or BM25-focused relevance filtering rather than raw content dumps.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:22:46.785Z","isFirstParty":false,"canonicalSlug":"mesh-agentdiet-dev-web-url-html-distillation-to-compact-agent-ready-67db2e29"}