Claude API

Overview

Anthropic's Claude API provides access to the Claude family of large language models, designed with safety and reliability at the core. Claude excels at complex reasoning, long-context analysis (up to 200K tokens), precise instruction following, and agentic tool use. The API supports streaming, function/tool calling, vision inputs, and structured JSON output. Available via direct API, AWS Bedrock, and Google Vertex AI.

Key Features

• 200K token context window
• Tool use / function calling
• Streaming responses
• Vision and multimodal inputs
• Structured JSON output
• Constitutional AI safety