Skip to main content

Your buyers are asking AI. Are you the answer?

Find out with OptimizeCamp →

Claude Opus 5.5

Anthropic's current Opus and default model for coding, agents, and knowledge work.

Claude Opus 5.5 specifications

ProviderAnthropic
Context window1,000,000 tokens (1.0M)
Input price$4.00 / 1M tokens
Output price$20.00 / 1M tokens
InputsText, Images
Reasoning modeYes
Vision (image input)Yes
Tool / function callingYes
Native real-time webNo
Open-weightNo

Pricing & context web-verified November 2026 — confirm on Anthropic's pricing page. The current Opus and Anthropic's default model. 128K max output.

What Claude Opus 5.5 is best for

  • Long-running agentic coding
  • Complex reasoning and analysis
  • Long-document and large-codebase work up to a 1M-token window
  • High-stakes writing

How to prompt Claude Opus 5.5

  • Use XML-style tags (<context>, <task>, <format>). Claude follows tagged structure very literally.
  • Thinking is always on. Control how hard it works with the effort setting, which defaults to medium.
  • Give explicit constraints ("do not…", "limit to…"). It respects them closely.
  • It handles a full 1M-token context window, so paste whole codebases or document sets rather than chunking.

Work with Claude Opus 5.5

Frequently asked questions

What is Claude Opus 5.5's context window?

Claude Opus 5.5 has a 1,000,000-token context window (about 1.0M tokens) — the maximum amount of text it can consider at once.

How much does Claude Opus 5.5 cost?

Via the Anthropic API, Claude Opus 5.5 costs $4.00 per 1M input tokens and $20.00 per 1M output tokens (web-verified November 2026). Output tokens cost more, so the length of the model's reply usually drives the bill.

Is Claude Opus 5.5 multimodal?

Yes — Claude Opus 5.5 accepts Text, Images as input, not just text.

Is Claude Opus 5.5 open-weight?

No — Claude Opus 5.5 is available only through the Anthropic API, not as downloadable weights.