Claude Opus 4.6

Claude Opus 4.6 is Anthropic's high-end model for difficult coding, planning, and slower expert reasoning. It is part of the claude-opus line, succeeding Claude Opus 4.5. It has a 1,000,000 token context window and a 128,000 token output limit. Pricing starts at $5.00 per million input tokens and $25.00 per million output tokens, with cached input at $0.50 per million. The weights are not open. It supports reasoning mode, tool calling, and accepts image, PDF, and text inputs, returning text.

Against Claude Opus 4.5: window 200K to 1M, input $0.71 to $5.00, output $3.57 to $25.00.

Range across the hosts that serve it: up to $6.00 per 1M input tokens.

• ·1,000,000 token context window
• ·128,000 token max output
• ·Reasoning mode for complex tasks
• ·Tool calling support
• ·Accepts image, PDF, and text inputs

• Reach for it for difficult coding
• Reach for it for planning
• Reach for it for expert reasoning

25 hosts serve this model at the price above · the maker's documentation

The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.

What is the context window?

The context window is 1,000,000 tokens, and the maximum output is 128,000 tokens.

How much does it cost?

Input costs from $5.00 per million tokens, output from $25.00 per million, and cached input from $0.50 per million.

Does it support image inputs?

Yes, it accepts image, PDF, and text inputs, and returns text. It also supports reasoning mode and tool calling.