Claude Opus 5

Flagship

claude-opus-5 · 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

Claude Opus 5 is Anthropic's latest flagship model, featuring a 1M token context window and 128K max output. It delivers next-generation deep reasoning, coding, and agentic capabilities, with extended thinking enabled by default (toggleable). Ideal for complex multi-step tasks, large-codebase analysis, and long-horizon agent workflows.

Capabilities

1M context window; Extended Thinking (on by default, toggleable); vision understanding; tool calling; MCP compatible; prompt caching; JSON mode; Function Calling; long-horizon agentic tasks.

Use Cases

Complex reasoning and research; large-codebase refactoring and code review; multi-step agent workflows; long-document analysis and summarization; advanced coding and debugging.

Limitations

Does not generate images; max output capped at 128K tokens; high-volume usage may require a quota; thinking adds latency on simple tasks.

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-5"
claude

Context Window

1M ctx

Thinking Mode

Toggleable

Overview

Claude Opus 5, Anthropic's latest flagship model with a 1M context window and 128K output. Next-gen deep reasoning, coding, and agent capabilities. Thinking is on by default and can be turned off.