Train AI on industry-leading Markdown with Zyte's new extraction mode. Zyte API can now extract a web page's main content directly as clean, structured Markdown for AI systems, RAG pipelines and developer workflows. Today, Zyte Group is introducing a new Zyte API output that turns web pages directly into clean Markdown - ready for AI systems, retrieval pipelines and developer workflows. Set "markdown": true in your request and Zyte API returns a plain Markdown string containing the page's primary content, leaving behind site-wide navigation, headers, footers and other boilerplate. It is the next step for pageContent, Zyte's existing feature that extracts the main content of almost any web page as clean plain text. The new Markdown output uses that same detection method behind the scenes, but preserves useful document structure such as headings, lists, tables, links and images. The new option comes with no separate charge; it's billed at the same rate as underlying Zyte API usage. Why Markdown - and why now? Raw HTML contains much more than the information an AI system needs. Tags, scripts, styles, navigation and repeated site furniture all consume tokens, increase processing costs and make downstream preparation harder. Converting a page to plain text solves much of that problem by stripping a page back to its words. It is ideal when you only need unformatted, readable content. But flattening everything into text also removes signals that help a machine understand how the document is organised. Markdown keeps the input lean while retaining lightweight semantics: * Headings show the hierarchy of ideas. * Lists preserve related items and sequences. * Tables keep relationships between rows and columns. * Links retain references and routes to supporting information. * Images can keep their descriptions and source URLs. That structure gives AI applications better material for chunking, retrieval and interpretation - without requiring them to process full-fat HTML first. How it compares to industry alternatives. In its internal benchmark of 35 HTML-to-Markdown tools across 299 real production pages, Zyte's method retained 95% of main content while removing 85% of unwanted page chrome such as navigation, footers and cookie notices. Among the 35 open-source and local tools tested, it achieved the highest recall of any dedicated extractor. For AI, that can really tell. Zyte API's Markdown averaged around 3,800 tokens per page, compared with more than 121,000 for the source HTML: a reduction of approximately 97%. The result is faithful, compact Markdown that AI agents can read and act on immediately. Zyte API's "markdown": true can do this because it benefits from the same primary-content identification logic introduced earlier with the pageContent option. By combining Zyte's proven web extraction with high-quality Markdown conversion, the feature solves both sides of agentic web access: reliably reaching difficult pages and delivering their content in a form that is ready for answering questions, powering RAG workflows or keeping knowledge bases current. You no longer need to ask developers to maintain CSS or XPath selectors. No separate HTML parser, content-cleaning library or conversion service is required in your pipeline. How to extract a page as Markdown. The simplest request needs only a URL and the new markdown output. 1# Store your Zyte API key in an environment variable 2export ZYTE_API_KEY="YOUR_ZYTE_API_KEY" 3 4curl \ 5 -user "$ZYTE_API_KEY:" \ 6 -header 'Content-Type: application/json' \ 7 -data '{ 8 "url": "https://example.com/article", 9 "markdown": true 10 }' \ 11 -compressed \ 12 https://api.zyte.com/v1/extract The response includes the Markdown as a top-level string: 1{ 2 "url": "https://example.com/article", 3 "statusCode": 200, 4 "markdown": "# Example page headline\n\nFirst paragraph...\n\n## Key findings\n\n- Finding one\n- Finding two" 5} By default, Zyte API uses: * scope: "mainContent" to return the primary content rather than the whole page. * extractFrom: "httpResponseBody" to work from the original HTTP response. Use browser-rendered HTML. For a page whose important content is rendered in the browser, set extractFrom to browserHtml: 1curl \ 2 -user "$ZYTE_API_KEY:" \ 3 -header 'Content-Type: application/json' \ 4 -data '{ 5 "url": "https://example.com/dynamic-page", 6 "markdown": true, 7 "markdownOptions": {8 "extractFrom": "browserHtml" 9} 10 }' \ 11 -compressed \ 12 https://api.zyte.com/v1/extract The Markdown is produced after any browser actions finish, so it can also capture content revealed by interactions in your request. Return the full page. Sometimes the surrounding navigation, footer or other page regions are part of the data you need. Set the scope to fullPage to convert the whole document instead: 1{ 2 "url": "https://example.com/article", 3 "markdown": true, 4 "markdownOptions": {5 "scope": "fullPage" 6} 7} Use mainContent for focused, token-efficient input. Use fullPage when completeness matters more than removing page furniture. Combine Markdown with structured page information. You can request markdown and pageContent together: 1{ 2 "url": "https://example.com/article", 3 "markdown": true, 4 "pageContent": true 5} This returns the main body as Markdown alongside pageContent fields such as the headline, breadcrumbs, header and footer navigation, pagination and next-page link. Zyte API analyses the page once and produces both outputs from the same pass. This combination is useful when an AI system should read the article body while your application handles navigation or crawl orchestration as structured data. Use it from python. 1import os 2import requests 3 4response = requests.post( 5 "https://api.zyte.com/v1/extract", 6 auth=(os.environ["ZYTE_API_KEY"], ""), 7 json={ 8 "url": "https://example.com/article", 9 "markdown": True, 10 "markdownOptions": {11 "scope": "mainContent" 12} 13}, 14) 15response.raise_for_status 16 17markdown = response.json["markdown"] 18print(markdown) From there, the result can go directly into a document store, vectorisation and chunking workflow, model-training dataset, prompt context or agent tool response. Get markdown through Zyte MCP. This same Markdown output powers the /fetch capability in Zyte's MCP server. Instead of writing an API request, connect an MCP-compatible agent to Zyte's hosted server: 1https://mcp.zyte.com/v1/mcp Then ask for the outcome in natural language: The agent can call Zyte MCP's fetch tool to retrieve the page through Zyte's web-access infrastructure and return clean Markdown directly in the conversation. This is particularly useful when the agent's built-in fetcher cannot access a protected or JavaScript-heavy page, or returns noisy HTML instead. Who benefits? AI and machine-learning teams. Prepare cleaner training and fine-tuning datasets while retaining document hierarchy. Markdown gives models more structural context than flat text without the overhead of HTML. RAG and knowledge-platform developers. Feed retrieval systems focused content with headings, lists, tables and links intact. Cleaner source documents can make chunking more predictable and retrieved passages easier to interpret. AI agent builders. Give agents compact, readable web content they can reason over and navigate. Combined with Zyte API's web access capabilities, Markdown output is particularly useful when an agent's built-in fetch tool cannot reliably reach or clean a page. Data engineers. Remove a chain of custom steps from ingestion pipelines. Zyte API can handle access, main-content detection and Markdown conversion in one request, reducing parser maintenance and integration work. Content intelligence and monitoring teams. Archive, compare, classify, summarise or translate web content in a consistent format - even when source sites use very different page templates. What can you build with it? * Training and fine-tuning corpora assembled from web content * RAG indexes and continuously updated knowledge bases * Research and coding agents that need dependable web context * Content-monitoring, classification and summarisation pipelines * Documentation ingestion and migration workflows * Competitive, market and product-intelligence systems * Lean web archives that preserve structure without storing noisy HTML Try Zyte API Product Marketing Valter Sciarrillo - Product Marketing @ Zyte

Decodo (Smartproxy) alternative for web scraping: 4 options compared [2026]. By ScrapeWise Team Decodo - the platform formerly known as Smartproxy - is a solid, mid-priced proxy-first option: residential, mobile, and datacenter pools plus a Site Unblocker and web scraping APIs. It's popular with teams that want proxies without Bright Data's enterprise weight or price. But "proxy-first" is also its boundary. You still write and maintain the scraping logic on top of the proxies, and if you need a source outside its API templates you're back to building. Teams look for alternatives when they want either a bigger pool, a different price point, or to stop operating scrapers altogether. Scrapewise compared Decodo against Bright Data, Oxylabs, Zyte, and ScrapeWise on what actually decides the switch. Which Decodo alternative is right for you? | Your situation | Best fit | | Need the largest proxy pool and unblocking scale | Bright Data | | Enterprise proxy + compliance focus | Oxylabs | | Want scraping-as-an-API with auto-extract | Zyte | | Don't want to run scrapers or proxies at all | ScrapeWise | | Cost is the trigger, still want to DIY | Zyte or ScrapeWise | Quick comparison. | Tool | Category | Proxy Pool | You Still Operate | Pricing | | Decodo | Proxy-first platform | Mid-large | Scraper logic | Per-GB / plan | | Bright Data | Proxy + data empire | Very large | Scraper logic | Per-GB / per-record | | Oxylabs | Enterprise proxy + APIs | Very large | Scraper logic | Enterprise | | Zyte | Scraping API | Managed | Some parsing | Per-request | | ScrapeWise | Managed data infra | Managed | Nothing | Pay-per-use | Bright Data vs Decodo. Best for: teams that hit Decodo's pool or unblocking limits at scale. Bright Data's residential and mobile pools are among the largest available, and its unlocker handles the hardest anti-bot targets. If you're outgrowing Decodo purely on scale or success rate, it's the natural step up - at a higher price and more product surface area. See its Bright Data alternative guide. Oxylabs vs Decodo. Best for: enterprises that want proxy scale with a compliance-first posture. Oxylabs is the enterprise heavyweight - large pools, scraper APIs, and a strong compliance story. It's a lateral-to-up move on cost from Decodo, so you'd choose it for scale and enterprise support rather than savings. Its Oxylabs alternative comparison has the detail. Zyte vs Decodo. Best for: teams that want scraping delivered as an API, not raw proxies. Zyte moves up the stack from proxies to a scraping API with automatic extraction, so you write less parsing code. If your friction is building scrapers rather than getting proxies, Zyte reduces more of the work than a proxy swap would. See the Zyte alternative guide. ScrapeWise vs Decodo. Best for: teams that want clean data without operating proxies or scrapers. Decodo gives you the raw access layer; you build everything on top. ScrapeWise is a managed data infrastructure - you name any URL and clean structured records land in your stack, with proxies, fingerprinting, and JavaScript rendering handled automatically. In internal testing (Apr 2026) it returned 97% SKU coverage with real-time (~2-minute) updates and 96% anti-bot success on Amazon EU, on pay-per-use pricing rather than per-GB. The difference from Decodo: no scraper to maintain and no source stuck outside a template. How to choose. * Is your bottleneck proxies or scrapers? Proxies | Bright Data/Oxylabs. Scrapers | Zyte or a managed feed. * Do you need to run infrastructure at all? If not, ScrapeWise removes both layers. * Is cost the trigger? Per-request (Zyte) or pay-per-use (ScrapeWise) can beat per-GB for spiky workloads. The bottom line. Decodo is a good mid-priced proxy platform, but it stops at the access layer. Go to Bright Data or Oxylabs for more pool and scale, Zyte for scraping-as-an-API, or ScrapeWise if you'd rather skip proxies and scrapers entirely and just receive clean data. Paste a URL your current tool cannot reach. See why teams switch to ScrapeWise. 97% accuracy benchmark, no per-SKU pricing. 97% accuracy on Amazon benchmarks · no credit card · book a 15-min call