{"uid":"cap_RiRhe-nMmntsFUpS_sRwU","slug":"token-intel-agentdiet-dev-web-url-distiller-with-bm25-budget-control-2115e121","name":"Web URL Distiller 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/pdf-extract)","url":"https://token-intel.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_A07Nn7HL_Qr_htjyP7e5D","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 accepts raw HTML) and distills it into compact, agent-ready tokens with configurable modes including markdown, structured JSON, skeleton outline, or BM25-focused budget excerpts.","exampleAgentPrompt":"Distill https://docs.stripe.com/payments into compact markdown — keep it under 2000 tokens and focus on anything related to payment intents.","exampleUseCases":[{"title":"Researching a competitor's pricing page","prompt":"Fetch and distill https://www.anthropic.com/pricing into structured markdown so I can quickly scan what's on the page without burning through my token budget."},{"title":"Budget-focused extraction for a support query","prompt":"I need you to pull the content from https://help.shopify.com/en/manual/orders/refunds and extract only the parts relevant to 'refund policy', keeping the output under 500 tokens."},{"title":"Skeleton outline of technical documentation","prompt":"Give me a skeleton outline of https://developers.google.com/maps/documentation so I can see the overall structure without reading the whole thing."}],"resultDescription":"Returns a distilled version of the webpage content in the requested mode (markdown, structured JSON, skeleton, or BM25 budget excerpt), along with ROI proof metrics including raw token count, distilled token count, tokens saved, compression ratio percentage, estimated LLM cost saved, and cache hit/miss status.","failureModes":["Invalid or unreachable URL returns an error status","mode=budget without a query or max_tokens may return unfiltered content","Very large pages may be truncated or exceed processing limits","Raw HTML input too large may be rejected","Non-public or paywalled URLs may return empty or partial content"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read a webpage but wants to minimize token consumption and LLM cost. It is especially useful when the target page is long or noisy and only a portion is relevant, or when a strict token budget must be respected. Use mode=budget with a BM25 query when you need keyword-focused excerpts. Prefer this over raw web fetch when compression ratio and token savings matter.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:30.139Z","isFirstParty":false,"canonicalSlug":"token-intel-agentdiet-dev-web-url-distiller-with-bm25-budget-control-2115e121"}