Claude Opus 4.8

Flagship

claude-opus-4-8 · 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

Anthropic's flagship model, Opus 4.8, delivers the strongest reasoning and coding capabilities available. With a 1M context window, 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-4-8"
claude

Context Window

1M ctx

Thinking Mode

Toggleable

Overview

Anthropic's flagship Opus 4.8, with a 1M context window and 128K output. The top choice for deep reasoning and long-horizon agent tasks. Thinking is on by default and can be turned off.