docs.anthropic.com

No JSON-LD blocks found. Add a <script type="application/ld+json"> with a schema.org type for this page.

Fix · Next.js: Emit JSON-LD from a Server Component or the Metadata API: a <script type="application/ld+json"> with Organization / Article / Product for the page.

Visible text is 0.5% of HTML weight (3694/737168 bytes). Low. Markup may be crowding out agent-usable text.

Fix: Heavy ad or navigation markup crowds out agent-usable text. Aim for a text-to-DOM ratio above 15%.

Meta description is 24 characters; aim for 50–200 so it's neither thin nor truncated.

Fix: Add `<meta name="description" content="...">` to your primary pages. Agents frequently use it as a summary.

TTFB 537ms. Acceptable.

Fix: Agents time out aggressively. Use edge caching for anonymous requests to cut TTFB below 800ms.

A Link: header is present but carries none of canonical/alternate/describedby — the relations agents consume.

Fix: Emit `Link:` headers for canonical, alternate-language, and describedby relations. Agents that fetch HEAD-only or stream-render rely on these.

No Content-Signal directives. Add e.g. `Content-Signal: ai-train=no, ai-summarize=yes` to declare granular AI usage policy beyond binary allow/disallow.

Fix: Add `Content-Signal:` directives to your robots.txt. This is the emerging standard (Cloudflare-driven) for declaring fine-grained AI usage policy beyond a binary allow/disallow.

<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "Organization",
  "name": "Documentation - Claude Platform Docs",
  "url": "https://docs.anthropic.com/",
  "description": "Claude API Documentation"
}
</script>

Documentation - Claude Platform Docs Claude Platform Docs Messages Managed Agents Admin Resources  Best practices Models & pricing CLI, SDKs, and libraries Claude API skill Release notes  API reference English   Console Log in   Browse  Claude Platform Start building with Claude Everything you need to integrate Claude into your applications. From first API call to production.  What do you want to build? ⌘K  Quickstart  Get API key  API reference Python TypeScript Go Java Ruby PHP C# cURL CLI  import anthropic client = anthropic.Anthropic() message = client.messages.create( model = "claude-opus-5" , max_tokens = 1024 , messages = [{ "role" : "user" , "content" : "Hello, Claude" }] ) for block in message.content: if block.type == "text" : print (block.text) Platform Choose how you build Pick the developer surface that matches your approach, and the infrastructure that fits your stack. Messages Direct model access. You construct every turn, manage conversation state, and write your own tool loop.  Quickstart   API reference   Client SDKs  Managed Agents Fully managed agent infrastructure. Deploy and manage autonomous agents in stateful sessions with persistent event history.  Quickstart   API reference  Define your agent  Amazon Bedrock  Google Cloud  Microsoft Foundry  Developer journey From idea to production Follow the lifecycle or jump to what you need. Messages Managed Agents 1 Get started  Quickstart   Get API key   Choose a model   Install an SDK   Try the Workbench  2 Build  Messages API  Thinking   Vision   Tool use  Web search   Code execution  Structured outputs   Prompt caching  Streaming  3 Evaluate and ship Prompting best practices   Run evals  Batch testing   Safety and guardrails   Rate limits and errors  Cost optimization  4 Operate  Workspaces and admin   API key management   Usage monitoring   Model migration  Models The Claude model family Choose the right model for your use case. Most capable Fable 5 claude-fable-5   Highest capability for the most demanding reasoning and long-horizon agentic work. Advanced Opus 5 claude-opus-5   Excellent for complex analysis, coding, and creative tasks requiring deep reasoning. Best balance Sonnet 5 claude-sonnet-5   Ideal balance of intelligence and speed for most production workloads. Fastest Haiku 4.5 claude-haiku-4-5   Lightning-fast responses for high-volume, latency-sensitive applications. Resources Keep learning  Courses  Interactive courses to master Claude.  Cookbook  Code samples and patterns.  Quickstarts  Deployable starter apps.  What's new Latest features and updates. Claude Code  An agentic coding assistant in your terminal. Claude Platform Docs Solutions AI agents Code modernization Coding Customer support Financial services Government Higher education K-12 teachers Life sciences Partners Claude on AWS Claude on Google Cloud Learn Blog Courses Use cases Connectors Customer stories Engineering at Anthropic Events Powered by Claude Service partners Startups program Company Anthropic Careers Economic Futures Research News Responsible Scaling Policy Security and compliance Transparency Learn Blog Courses Use cases Connectors Customer stories Engineering at Anthropic Events Powered by Claude Service partners Startups program Help and security Availability Status Support Discord Terms and policies Privacy policy Responsible disclosure policy Terms of service: Commercial Terms of service: Consumer Usage policy

Running AI agents of your own? AgentSpeed also monitors them in production — every run, its latency, cost, and failures, with alerts when something breaks. Free for 10,000 events a month, no credit card.