{"uid":"cap_9i5L72CgZXhHxoA_peZhy","slug":"agentdiet-context-diet-html-semantic-distillation-cffe406e","name":"AgentDiet Context Diet – HTML Semantic Distillation","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://agentdiet.dev/v1/context-diet)","url":"https://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":["x402"],"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":"unknown","protocol":"x402","network":"base","amountUsd":null,"per":"call","confidence":"unknown"},{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_HAbwbS4-LWBBYPYCUhYR_","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null},{"uid":"pm_a8XscDGRP36Iqlo_JA2q2","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Strips 85–97% of HTML token bloat from a given URL, returning only the semantically meaningful content for LLM consumption","exampleAgentPrompt":"Fetch https://example.com/article and strip out all the HTML token bloat so I get just the clean, meaningful text — I need to fit it into my LLM context window.","exampleUseCases":[{"title":"LLM context window preprocessing","prompt":"I'm about to feed this page https://techcrunch.com/2025/01/15/some-article into GPT-4 but it's way too many tokens — can you distill it down to just the semantic content first?"},{"title":"Agent web research pipeline","prompt":"My agent needs to read and summarize this docs page at https://docs.stripe.com/api — can you pull just the meaningful text from it using GET mode so there's no HTML junk?"},{"title":"RAG ingestion cleaning","prompt":"Before I index this blog post at https://myblog.com/post/ai-trends into my vector database, strip the HTML noise out of it so I'm only embedding the actual content."}],"resultDescription":"A token-compressed, semantically distilled version of the target webpage's content — stripped of 85–97% of HTML markup, navigation, scripts, and boilerplate — returning only the meaningful prose, headings, and data for direct LLM ingestion.","failureModes":["URL is unreachable or returns a non-200 status — endpoint may return an error or empty content","URL points to a JavaScript-heavy SPA that requires client-side rendering — distilled output may be sparse","Paywalled or auth-gated pages return only login-wall content","Very large pages may time out or return partial content","Malformed URL input causes a 400-level error","The page is already minimal HTML with little to strip, resulting in near-identical output"],"whenToPreferThis":"Choose this endpoint when you need to feed a webpage into an LLM but the raw HTML is too token-heavy for your context window. It is purpose-built for token optimization and semantic distillation, making it ideal for RAG pipelines, agent web-browsing steps, or any workflow where HTML bloat would waste tokens or exceed context limits. Prefer this over generic web scrapers when token efficiency is the primary concern.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-20T12:48:16.080Z","isFirstParty":false,"canonicalSlug":"agentdiet-context-diet-html-semantic-distillation-cffe406e"}