{"uid":"cap_j5BTdXQ5JV7MS6znGHb5V","slug":"json-repair-agentdiet-dev-webpage-distiller-bm25-budget-controlled-dec2ddba","name":"Webpage Distiller – BM25 Budget-Controlled Web Content Extraction","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://json-repair.agentdiet.dev/v1/webpage-distiller)","url":"https://json-repair.agentdiet.dev/v1/webpage-distiller?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_B4wwbGIjligCAgKVHmz1H","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"json-repair.agentdiet.dev","brandSlug":"json-repair-agentdiet-dev-mpp","brandBaseUrl":"https://json-repair.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or raw HTML and distills it into compact, agent-ready tokens using markdown, structured, skeleton, or BM25-budget modes with measurable token compression.","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/payments and distill it into compact markdown, keeping it under 2000 tokens and focusing on the BM25 query 'payment intents'?","exampleUseCases":[{"title":"Token-budget research for LLM pipeline","prompt":"Pull https://openai.com/pricing and give me a budget-mode distillation focused on 'API pricing tiers' with a strict ceiling of 1500 tokens so I don't blow my context window."},{"title":"Structured data extraction from product page","prompt":"Distill https://aws.amazon.com/ec2/instance-types/ in structured mode so I get the pricing tables and metadata as clean JSON instead of raw HTML."},{"title":"Skeleton outline of documentation site","prompt":"Fetch https://docs.anthropic.com/en/docs/overview and return a skeleton outline so I can quickly see the section structure without reading the full content."}],"resultDescription":"Returns a JSON object containing the distilled content (in the requested mode: markdown text, structured JSON tables/metadata, skeleton outline, or BM25-filtered excerpt), an ROI proof block showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD, plus optional billing and cache hit/miss metadata.","failureModes":["Invalid or unreachable URL returns an error status","HTML too large or malformed may produce incomplete distillation","mode=budget without a query or max_tokens may fall back to default behavior","Paywalled or JavaScript-heavy pages may yield minimal or empty content","Payment failure (x402) if agent_id or USDC balance is insufficient","Rate limiting if called too frequently without valid billing credentials"],"whenToPreferThis":"Choose this endpoint when you need to inject live web content into an LLM prompt but want to minimize token usage and cost — especially when the raw page would exceed your context window. It is superior to raw fetch-and-paste when token budget control matters, when you need BM25-focused relevance filtering on a specific query, or when you want structured JSON tables extracted from HTML rather than unformatted markup. It is also ideal when you need measurable compression ROI proof for cost accounting in agent pipelines.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:41.720Z","isFirstParty":false,"canonicalSlug":"json-repair-agentdiet-dev-webpage-distiller-bm25-budget-controlled-dec2ddba"}