Claude Sonnet 5

Claude Sonnet 5 is Anthropic’s most agentic Sonnet model. It brings performance that recently required larger, more expensive models to coding, tool use, and everyday work, at Sonnet’s speed and price. In some cases it matches the capability of Anthropic’s larger Opus models, while staying in the mid-tier price band.

Sonnet 5 is built for agents. It can plan, use tools like browsers and terminals, and run autonomously across multi-step tasks. That makes it a good fit for production coding workflows, customer-facing agents, content generation at scale, and real-time research.

What it’s good at

• Coding. Strong across the whole development lifecycle: writing code, using tools, and staying focused on long multi-step tasks.
• Agents and tool use. Plans ahead and drives tools like browsers and terminals to complete tasks on its own.
• Reasoning. Handles math, analysis, and specialized knowledge across fields like finance, law, medicine, and science.
• Vision. Accepts an image alongside your prompt for tasks like reading diagrams, transcribing text, and describing pictures.

Thinking effort

Sonnet 5 can think before it answers. The effort input controls how much:

• low (default) turns thinking off for the fastest, cheapest responses.
• medium, high, xhigh, and max let the model reason more before responding, which improves quality on hard coding and agentic tasks but is slower and uses more output tokens.

Inputs

• prompt — your input prompt.
• system_prompt — an optional system prompt to steer the model’s behavior.
• image — an optional image to send with your prompt. Images are priced as (width px × height px) / 750 input tokens.
• max_tokens — the maximum number of output tokens.
• effort — how much thinking the model does before responding.
• max_image_resolution — scales the image down before sending it, to save time and money.

Pricing

Sonnet 5 is billed per token: $2 per million input tokens and $10 per million output tokens.

For more details, see the Claude Sonnet 5 announcement.