Claude Opus 4.8 ships with 1M token context; adaptive thinking reduces waste

We've launched Claude Opus 4.8 (claude-opus-4-8), our most capable generally available model. Key features:

• Supports 1M token context window by default on Claude API, Amazon Bedrock, Google Cloud, and Microsoft Foundry
• 128k max output tokens
• Same tools and platform features as Claude Opus 4.7
• Mid-conversation system messages now supported: send role: "system" messages after user turns to preserve prompt cache hits when instructions change
• Effort parameter defaults to high across all surfaces
• Minimum cacheable prompt length for prompt caching reduced to 1,024 tokens
• Adaptive thinking triggers reasoning only when needed, reducing wasted thinking tokens
• Supports high-resolution image input (up to 2576 pixels on long edge)
• Task budgets now supported
• Advisor tool now supported
• Computer use now supported