Claude Opus 5.5

Claude Opus 5.5 is Anthropic’s current Opus model, built for long-running agentic coding and knowledge work. Anthropic recommends it as the starting point for most workloads. It costs 20% less per token than Claude Opus 5, and Anthropic says it gets the same work done with fewer tokens.

Use it for complex, multi-step tasks: writing and reviewing code, planning and driving tools across long agentic runs, and research or analysis in fields like finance, law, medicine, and science.

What it’s good at

• Coding. Writing, refactoring, and debugging code, and staying on track through long, hard tasks.
• Agents. Plans ahead and works through multi-step tasks with little supervision.
• Reasoning. Math, analysis, and specialized knowledge across technical and professional domains.
• Vision. Accepts an image alongside your prompt for tasks like reading diagrams, transcribing text, and describing pictures.

Thinking effort

Opus 5.5 always thinks before it answers. You can’t turn thinking off, but you can control how much it does with the effort input:

• low (default) keeps thinking short, for the fastest and cheapest responses.
• medium is Anthropic’s recommended level for most work.
• high, xhigh, and max let the model reason more, which helps on the hardest coding and agentic tasks but is slower and uses more output tokens.

Thinking tokens count toward max_tokens and are billed as output tokens. At xhigh or max, Anthropic suggests setting max_tokens to 64,000 or more so the model has room to think and answer.

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, including thinking. Up to 128,000.
• effort: how much thinking the model does before responding.
• max_image_resolution: scales the image down before sending it, to save time and money.

Specs

• Context window: 1 million tokens
• Maximum output: 128,000 tokens
• Knowledge cutoff: June 2026

Pricing

Opus 5.5 is billed per token: $4 per million input tokens and $20 per million output tokens.

If Anthropic’s safety systems decline a request, the run fails with a content error instead of returning an empty response.