{"uid":"cap_jOXCK_TVRbrA5eaclN_L3","slug":"json-repair-agentdiet-dev-web-url-html-distillation-with-bm25-budget-66fa0cd9","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/v1/context-diet)","url":"https://json-repair.agentdiet.dev/v1/context-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_eD8LzXXvPfzB4qRVbYwYi","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 and compresses a webpage URL or raw HTML into compact, agent-ready tokens using markdown, structured, skeleton, or BM25-focused budget modes","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments into compact markdown under 800 tokens, focusing on the query 'payment intent lifecycle' using budget mode?","exampleUseCases":[{"title":"Summarize documentation under token budget","prompt":"Distill https://docs.openai.com/api-reference into budget mode focused on 'function calling', keeping it under 500 tokens so I can fit it in my prompt."},{"title":"Extract structured data from company page","prompt":"Fetch https://example.com/pricing and convert it into structured JSON tables so I can parse their pricing tiers without reading the whole page."},{"title":"Skeleton outline of long article","prompt":"Give me a skeleton outline of https://en.wikipedia.org/wiki/Large_language_model — just the headings and key structure, not the full content."}],"resultDescription":"Returns a 'data' object containing the distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked budget excerpt), an 'roi_proof' object with raw token count, distilled token count, tokens saved, compression ratio percentage, ROI multiplier, and estimated LLM cost saved in USD, plus optional cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","max_tokens below minimum of 20 is rejected","mode=budget without a query may return unfiltered or poorly scoped content","Very large pages may be truncated or slow to process","Payment failure via x402 blocks the request","HTML-only input with url missing returns a validation error since url is required"],"whenToPreferThis":"Choose this endpoint when you need to fit a webpage's content into a limited LLM context window, want to reduce token costs when reading web pages, or need BM25-focused extraction of only the most relevant passages from a large document. Especially valuable when processing documentation pages, long articles, or any HTML where you care about a specific topic and want to discard boilerplate noise.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:26:13.213Z","isFirstParty":false,"canonicalSlug":"json-repair-agentdiet-dev-web-url-html-distillation-with-bm25-budget-f80b20bd"}