{"uid":"cap_-221iqdnQXa9plWCG5aYp","slug":"json-repair-agentdiet-dev-web-url-distillation-bm25-budget-extraction-c5a7bfdd","name":"Web URL Distillation & BM25 Budget 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/pdf-extract)","url":"https://json-repair.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_MuZio5BkueQEBJFUPYcQZ","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 webpage or raw HTML and distills it into compact, agent-ready tokens with optional BM25 budget control for token-efficient LLM consumption","exampleAgentPrompt":"Can you distill https://stripe.com/docs/api into compact markdown using budget mode, focusing on 'payment intents', and keep it under 500 tokens?","exampleUseCases":[{"title":"Token-efficient doc ingestion for LLM","prompt":"Distill the Stripe docs at builtin://stripe-docs into structured markdown so I can feed just the relevant parts to my model — use budget mode with a 300-token ceiling and focus the BM25 query on 'webhooks'."},{"title":"Extracting tables from a financial report page","prompt":"Fetch https://example.com/annual-report and distill it in structured mode so I get clean JSON tables and metadata I can analyze — I want to see revenue figures without wading through all the prose."},{"title":"Skeleton outline of a competitor landing page","prompt":"Grab https://competitor.com and give me a skeleton outline of the page structure — headings, sections, and key content blocks only — so I can quickly understand how they've laid out their pitch."}],"resultDescription":"Returns a status field, distilled content in the data object (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), cache hit/miss info, billing details, and an roi_proof object showing raw vs. distilled token counts, tokens saved, compression ratio, and estimated LLM cost saved in USD.","failureModes":["Invalid or unreachable URL returns an error status and empty data","max_tokens below minimum (20) triggers a validation error","BM25 query provided without mode=budget may be ignored","Raw HTML injection via html param may fail if malformed","Payment failure via x402 returns HTTP 402 with no content","Paywalled or bot-blocked pages may return incomplete distillation"],"whenToPreferThis":"Choose this endpoint when you need to feed web content to an LLM but want to minimize token usage and cost — especially when the target page is verbose or HTML-heavy. It is ideal for agent pipelines that need to retrieve and process many pages economically, or when you need structured tables and metadata extracted from web content rather than raw HTML. The BM25 budget mode makes it uniquely suited for focused retrieval where only query-relevant content should be passed downstream.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:14.523Z","isFirstParty":false,"canonicalSlug":"json-repair-agentdiet-dev-web-url-distillation-bm25-budget-extraction-c5a7bfdd"}