{"uid":"cap_ZSNi0u7lKL7WITPm3AwMa","slug":"workflows-agentdiet-dev-agentdiet-web-url-distiller-ce83a961","name":"AgentDiet Web URL Distiller","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://workflows.agentdiet.dev/v1/distill)","url":"https://workflows.agentdiet.dev/v1/distill?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_eoV3vVrUzz1jIo34DnyCn","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"workflows.agentdiet.dev","brandSlug":"workflows-agentdiet-dev-mpp","brandBaseUrl":"https://workflows.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and compresses any webpage URL (or raw HTML) into compact, agent-ready tokens using BM25 budget control and multiple distillation modes","exampleAgentPrompt":"Fetch this URL https://stripe.com/docs/payments and distill it into compact markdown, keeping it under 500 tokens and focusing on the query 'payment intents setup'.","exampleUseCases":[{"title":"Research article distillation for RAG pipeline","prompt":"Grab this long Wikipedia article at https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) and distill it into clean markdown — I want to inject it into my agent context without blowing my token budget."},{"title":"Budget-constrained doc lookup for coding agent","prompt":"Pull the Stripe docs page at builtin://stripe-docs and give me a budget distillation focused on 'webhook signature verification', capped at 300 tokens so my coding agent can reference it inline."},{"title":"Structured data extraction from a product page","prompt":"Fetch https://openai.com/pricing and distill it in structured mode so I get the pricing tables and metadata in a clean JSON format my agent can parse directly."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown, structured JSON, skeleton outline, or BM25 excerpt depending on mode), along with an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd. Also includes cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","max_tokens below minimum of 20 rejected with validation error","mode=budget without a query param may return unfiltered content","Raw HTML too large may exceed processing limits","Paywalled or JS-rendered pages may return incomplete content","x402 payment failure returns 402 with payment instructions"],"whenToPreferThis":"Choose this endpoint when your agent needs to ingest web content within a strict token budget — especially for RAG pipelines, context injection, or cost-sensitive LLM workflows. Prefer it over raw HTML scraping when you need automatic compression, BM25-focused relevance filtering, or structured extraction from arbitrary URLs. Particularly valuable when LLM context windows are constrained or when you want to minimize per-call token costs.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:40:43.035Z","isFirstParty":false,"canonicalSlug":"workflows-agentdiet-dev-agentdiet-web-url-distiller-ce83a961"}