{"uid":"cap__516umbXujP_jq21yWhfV","slug":"hn-pulse-agentdiet-dev-agentdiet-web-distiller-aba444ac","name":"AgentDiet Web Distiller","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://hn-pulse.agentdiet.dev/api/diet)","url":"https://hn-pulse.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_XDpt-54Ax65ZNHElnJ_f8","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"hn-pulse.agentdiet.dev","brandSlug":"hn-pulse-agentdiet-dev-mpp","brandBaseUrl":"https://hn-pulse.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or raw HTML and compresses it into compact, agent-ready tokens using BM25 budget control and multiple distillation modes","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into clean markdown using budget mode, focusing on 'payment intents', and cap it at 500 tokens.","exampleUseCases":[{"title":"Token-budget doc extraction for LLM pipelines","prompt":"Fetch https://docs.openai.com/api-reference and distill it into budget mode focused on 'embeddings endpoint', keeping it under 300 tokens — I want to feed only the relevant chunk to my model."},{"title":"Structured table extraction from a product page","prompt":"Pull the page at https://aws.amazon.com/ec2/pricing/ and extract it in structured mode so I get the pricing tables as clean JSON I can parse."},{"title":"Skeleton outline of a long article","prompt":"Take this URL https://en.wikipedia.org/wiki/Large_language_model and give me a skeleton outline so I can see the document structure before deciding what section to deep-dive."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Optionally includes billing details and cache status (HIT/MISS).","failureModes":["Invalid or unreachable URL returns an error status","HTML fetch timeout for slow or blocked pages","Token budget too small (max_tokens below 20) rejected by schema validation","BM25 query provided without mode=budget may be ignored","Raw HTML too large may hit processing limits","Payment/402 failure if agent wallet is insufficient"],"whenToPreferThis":"Choose this endpoint when you need to feed web page content to an LLM but want to minimize token consumption and cost. It is especially valuable when working with long documentation pages, pricing tables, or articles where only the most relevant sections matter. Prefer it over raw web fetching whenever token budgets are a concern or when you need structured JSON or skeleton outlines rather than raw HTML.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:13.111Z","isFirstParty":false,"canonicalSlug":"hn-pulse-agentdiet-dev-agentdiet-web-distiller-aba444ac"}