{"version":"1.0.83","anchor":"extended-beta-features-for-first-party-and-vertex-api-users","canonical_anchor":"extended-beta-features-for-first-party-and-vertex-api-users","heading":"Extended Beta Features for First-Party and Vertex API Users","tier":null,"area":null,"scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/1.0.83\/e\/extended-beta-features-for-first-party-and-vertex-api-users","release_url":"https:\/\/changelogs.core-directive.com\/v\/1.0.83","markdown":"### Extended Beta Features for First-Party and Vertex API Users\n\n**What:** Users connecting through Anthropic's API or Google Vertex AI now have access to previously restricted beta features **How to use:**\n\n`# For Anthropic API (default - no special configuration needed) claude \"Analyze this 800,000 token codebase\" # For Google Vertex AI export CLAUDE_CODE_USE_VERTEX=true claude \"Use interleaved thinking to solve this complex problem\"` **Details:**\n\n- Enables \"interleaved-thinking-2025-05-14\" beta feature for enhanced reasoning capabilities\n- Enables \"context-1m-2025-08-07\" beta feature supporting up to 1 million token context windows\n- These features are automatically included in API requests when not using AWS Bedrock\n- No additional flags or configuration needed - features activate automatically based on your backend"}