Looking just to chat with Claude? Visit claude.ai!

Claude is a family of large language models developed by Anthropic and designed to revolutionize the way you interact with AI. Claude excels at a wide variety of tasks involving language, reasoning, analysis, coding, and more. Our models are highly capable, easy to use, and can be customized to suit your needs.

This documentation is designed to help you get the most out of Claude, whether you’re a beginner just getting started with AI or an experienced developer looking to build advanced applications. You’ll find clear explanations, helpful examples, best practices, and links to additional resources.

If you’re seeking immediate inspiration, visit our prompt library!

API reference

Get all the details on API endpoints, request/response formats, parameters, and more on our API reference pages.

Intro to Claude models

Claude 3 Haiku, Sonnet, and Opus are the next generation of Claude models. They are state-of-the-art text and vision models that can generate human-like text outputs based on both image and text inputs. With powerful vision capabilities, they open up exciting possibilities for computer vision and image understanding applications. Opus, the most powerful model, offers unparalleled intelligence, reasoning, and creativity on a wide range of tasks, while Haiku offers plenty of capability at very high speed and low cost. Sonnet offers a great balance between the two.

Getting started

Jump right in with our quickstart guide and learn how to make your first API call in minutes. Or check out the prompt library or our intro to prompting guide to learn more about prompting.

Prompt engineering

Learn best practices and strategies for designing effective prompts to get the most out of Claude with our prompt engineering guide.

Anthropic Cookbook

If you learn prompting better in combination with code and applied examples of interesting use cases, visit the Anthropic Cookbook instead. There you’ll find copy-able code that demonstrate how to use Claude in neat and effective ways in more advanced scenarios, such as uploading PDFs, tool use and function calling, embeddings, and more.

With the developer Console and the claude.ai chatbot, you can experiment with prompts right in your browser.

Claude 3 technical presentation

If you’re more of a visual learner, check out our Claude 3 technical presentation slides for a visual overview of some of the content also covered in our documentation.

There is also a Bedrock version of these slides.

Key capabilities

Our models can assist with all kinds of tasks:

  • Content generation
  • Image interpretation
  • Summarization
  • Classification
  • Translation
  • Sentiment analysis
  • Code explanation & generation
  • Question answering
  • Creative writing
  • Interpretation
  • And much more

Explore these capabilities in greater depth in our use cases and capabilities guide.


Have questions or need help? Contact support or join the Discord community server to get assistance, give feedback, and share your projects!