Back
AnthropicClaude API
We've launched Claude Sonnet 4.5, our best model for complex agents and coding, with the highest…
AI summary
Written by AI from the official notes. Check them for exact details.Claude Sonnet 4.5 has been launched with improved capabilities for complex tasks and coding.
- Launch of Claude Sonnet 4.5 for complex agents and coding.
- Global endpoint pricing introduced for Amazon Bedrock and Vertex AI.
- New stop reason for maximum token requests without input size calculation.
- Beta launch of memory tool for storing conversation information.
- Beta launch of context editing for managing conversation context.
Why it matters: Developers and users of AI tools should explore these enhancements for improved functionality and efficiency.
Full release notes5 changes
- We've launched Claude Sonnet 4.5, our best model for complex agents and coding, with the highest intelligence across most tasks. Learn more in the models overview.
- We've introduced global endpoint pricing for Amazon Bedrock and Vertex AI. The Claude API (1P) pricing is unaffected.
- We've introduced a new stop reason
model_context_window_exceededthat allows you to request the maximum possible tokens without calculating input size. Learn more in Handling stop reasons. - We've launched the memory tool in beta, enabling Claude to store and consult information across conversations. Learn more in Memory tool.
- We've launched context editing in beta, providing strategies to automatically manage conversation context. The initial release supports clearing older tool results and calls when approaching token limits. Learn more in Context editing.