{"uid":"cap_1tImaVHbzxt7rij60lNQO","slug":"json-repair-agentdiet-dev-web-url-html-distillation-with-bm25-budget-b732dbd8","name":"Web URL & HTML Distillation 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://json-repair.agentdiet.dev/api/diet)","url":"https://json-repair.agentdiet.dev/api/diet?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___3E0ejensmUEGvxMP6qx","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 strict token ceiling control.","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into compact markdown using budget mode, focused on 'payment intents', and keep it under 500 tokens.","exampleUseCases":[{"title":"Token-budget extraction for LLM pipelines","prompt":"Grab https://openai.com/pricing and distill it in budget mode with the query 'GPT-4 token cost' capped at 300 tokens — I want to feed only the relevant pricing info to my model."},{"title":"Structured data extraction from a product page","prompt":"Distill https://www.notion.so/product into structured mode so I get JSON tables and metadata about Notion's features without all the bloated HTML."},{"title":"Skeleton outline of a long documentation page","prompt":"Fetch https://docs.aws.amazon.com/lambda/latest/dg/welcome.html and give me a skeleton outline so I can quickly understand the top-level structure of the AWS Lambda docs."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (markdown, structured JSON, skeleton, or BM25 excerpt depending on mode), plus an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, ROI multiplier, and estimated LLM cost saved in USD. Also includes optional cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","mode=budget without a query or max_tokens may return unfiltered content","Very large HTML payloads may exceed processing limits","Paywalled or JavaScript-rendered pages may return incomplete distillation","Missing required 'url' parameter returns a 400-level error","x402 payment not fulfilled results in a 402 Payment Required response"],"whenToPreferThis":"Choose this endpoint when you need to feed webpage content to an LLM but want to minimize token usage and cost — especially when you have a strict token budget or a specific BM25 keyword focus. It is ideal over raw web scraping when you need clean markdown or structured JSON output rather than raw HTML. Prefer it over generic summarization APIs when you need quantified ROI metrics (tokens saved, compression ratio) and support for multiple distillation modes including skeleton outlines and structured tables.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:58.603Z","isFirstParty":false,"canonicalSlug":"json-repair-agentdiet-dev-web-url-html-distillation-with-bm25-budget-f80b20bd"}