{"uid":"cap_XUJVolElZA-L1HGDI_Tv8","slug":"agentdiet-html-to-markdown-converter-df8fe376","name":"AgentDiet HTML to Markdown Converter","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://agentdiet.dev/v1/html-to-markdown)","url":"https://agentdiet.dev/v1/html-to-markdown?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_ZzRzeW8hxgRxHxvpCdP8M","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null},{"uid":"pm_UAmF8kTtv9Xa5ediFwDNg","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":"Converts a web page's HTML into clean Markdown by stripping 85-97% of token bloat, making content LLM-ready","exampleAgentPrompt":"Can you fetch https://en.wikipedia.org/wiki/Large_language_model and convert it to clean Markdown, stripping all the HTML bloat so I can use it in my LLM prompt?","exampleUseCases":[{"title":"LLM context window stuffing from web","prompt":"Grab the page at https://docs.openai.com/api-reference and convert it to markdown so I can paste it into my GPT-4 prompt without hitting token limits."},{"title":"Summarize an article without HTML noise","prompt":"Fetch https://techcrunch.com/2024/05/10/ai-agents-explainer/ and give me just the clean readable text in markdown — strip out all the navigation, ads, and HTML tags."},{"title":"Research pipeline preprocessing","prompt":"I need you to pull https://www.sec.gov/cgi-bin/browse-edgar?action=getcompany&CIK=AAPL and convert the HTML into markdown so my research agent can process it cleanly."}],"resultDescription":"Returns the fetched web page's content as clean Markdown with navigation, scripts, ads, and HTML markup stripped out, reducing token count by 85-97% compared to raw HTML — ideal for feeding into LLM context windows or downstream text processing pipelines.","failureModes":["URL is unreachable or returns a non-200 status — endpoint may return an error or empty content","Dynamic JavaScript-rendered pages may not be fully captured since the fetch is likely static HTML only","Very large pages may be truncated or slow to process","Paywalled or login-protected pages will return minimal or no content","Invalid or malformed URL input causes a bad request error"],"whenToPreferThis":"Choose this endpoint when you need to fetch a live web page and immediately get a token-efficient, LLM-ready Markdown representation of its content. It is ideal for AI agent pipelines that must ingest web content without blowing up context windows, compared to raw HTML scraping or full browser automation tools. Prefer it over generic HTML scrapers when token reduction and semantic distillation quality matter.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-20T12:48:16.082Z","isFirstParty":false,"canonicalSlug":"agentdiet-html-to-markdown-converter-df8fe376"}