Claude Opus 4.6

claude-opus-4-6 · Anthropic · text

Back to Models Back to Docs

Platform

Anthropic

Visit Official Site

API Pricing

Input / 1M

$5/M$3.5/M30% OFF

Output / 1M

$25/M$17.5/M30% OFF

Cache Read / 1M

$0.5/M$0.35/M30% OFF

Overview

Opus 4.6 is Anthropic's flagship model, delivering the strongest reasoning and coding capabilities. With 1M context, it supports Extended Thinking, Computer Use, visual understanding, and tool calling. Built for complex agent tasks, long-document analysis, and demanding software engineering.

Capabilities

1M context; Extended Thinking; Computer Use; visual understanding (images/PDFs); tool calling; MCP compatible; prompt caching (cache_read 10%, cache_write 1.25×); JSON mode; Function Calling.

Use Cases

Complex software engineering; multi-step agent tasks; long-document analysis (codebases/PDFs); research assistants; enterprise knowledge base Q&A; automated office operations.

Limitations

Does not generate images; max_tokens capped at 32K; high concurrency requires an enterprise quota; Extended Thinking consumes additional tokens; Computer Use is still in beta.

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-opus-4-6"
claude

Context Window

200K ctx

Thinking Mode

Not supported

Overview

Most powerful model for highly complex tasks