{"uid":"cap_AACTUIVphjgdF4MJYgE_U","slug":"alpha-stream-agentdiet-dev-agentdiet-dom-stripper-web-url-distiller-09a9e5de","name":"AgentDiet DOM Stripper – Web URL Distiller","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://alpha-stream.agentdiet.dev/v1/dom-stripper)","url":"https://alpha-stream.agentdiet.dev/v1/dom-stripper?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_u8-MtO93Shn3X2M8-HkQ4","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"alpha-stream.agentdiet.dev","brandSlug":"alpha-stream-agentdiet-dev-mpp","brandBaseUrl":"https://alpha-stream.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-controlled extraction modes","exampleAgentPrompt":"Can you distill https://stripe.com/docs/api into compact markdown — I want to stay under 2000 tokens and focus on the authentication section, so use budget mode with that as the BM25 query.","exampleUseCases":[{"title":"Summarize documentation for agent context","prompt":"Pull down the Stripe docs at https://stripe.com/docs/payments and compress them into clean markdown I can feed into my agent's context window — use budget mode with 'payment intents' as the focus query and cap it at 1500 tokens."},{"title":"Extract structured tables from a pricing page","prompt":"Go to https://openai.com/pricing and distill it into structured mode so I get the pricing tables and metadata in JSON without all the surrounding HTML clutter."},{"title":"Generate skeleton outline of a long article","prompt":"Distill https://en.wikipedia.org/wiki/Large_language_model into skeleton mode so I can see the high-level outline and section headers without reading the full content."}],"resultDescription":"Returns a 'data' object containing the distilled content in the requested format (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd, along with optional cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","HTML fetch blocked by target site (403/429) yields no content","mode=budget with no query or max_tokens may return unfiltered result","Very large pages may exceed internal processing limits","Raw HTML input too large may be rejected","Token budget too low (below 20) is rejected by schema validation"],"whenToPreferThis":"Choose this endpoint when your agent needs to read a webpage but must minimize token consumption and LLM cost — especially for long documentation pages, news articles, or data-heavy sites. The BM25 budget mode is uniquely valuable when you need topically focused extraction within a strict token ceiling. Prefer this over generic web scrapers when you need the output to be immediately consumable by an LLM without further cleaning, and when compression metrics (tokens saved, cost saved) matter to your pipeline.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:37.621Z","isFirstParty":false,"canonicalSlug":"alpha-stream-agentdiet-dev-agentdiet-dom-stripper-web-url-distiller-09a9e5de"}