Claude Sonnet 5

Recommended

claude-sonnet-5 · Anthropic · text

Back to Models Back to Docs

Platform

Anthropic

Visit Official Site

API Pricing

Input / 1M

$2/M$1.4/M30% OFF

Output / 1M

$10/M$7/M30% OFF

Cache Read / 1M

$0.2/M$0.14/M30% OFF

Overview

Sonnet 5 is Anthropic's recommended model, balancing intelligence and speed. With 1M context and support for Extended Thinking, visual understanding, tool calling, and Computer Use, it is the best choice for everyday coding, document analysis, and agent tasks.

Capabilities

1M context; Extended Thinking; Computer Use; visual understanding; tool calling; MCP compatible; prompt caching; JSON mode; Function Calling.

Use Cases

Everyday code generation and refactoring; multi-turn conversational agents; long-document analysis; image understanding; structured data extraction; enterprise customer support and assistants.

Limitations

Does not generate images; max_tokens capped at 64K; high concurrency requires an enterprise quota; Extended Thinking consumes additional tokens.

Examples

Claude Code

Anthropic official CLI coding agent. Multi-file edits, tool use, long-context reasoning.

Terminal

export ANTHROPIC_AUTH_TOKEN="YOUR_API_KEY"
export ANTHROPIC_BASE_URL="https://api.robovai.com"
export ANTHROPIC_MODEL="claude-sonnet-5"
claude

Context Window

1M ctx

Thinking Mode

Toggleable

Overview

Claude Sonnet 5, with a 1M context window and 128K output. The best balance for coding and everyday agent tasks. Thinking is on by default and can be turned off.